Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? | Paper Citation Record

Observation 4f04a85d-f721-4118-ab82-9cd701d6708e · outbound

This paper cites GPT-4 Technical Report.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:40.321323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ec5b587-af49-4a0a-97c2-445190142c89 · outbound

This paper cites JGCL: Joint self-supervised and supervised graph contrastive learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? JGCL: Joint self-supervised and supervised graph contrastive learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:40.392994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad0fb807-3677-4f47-9815-824740b2d791 · outbound

This paper cites CrisisMMD: Multimodal twitter datasets from natural disasters.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? CrisisMMD: Multimodal twitter datasets from natural disasters

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:40.497124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ab86eed-f9d0-4e4b-9a4d-66739e4dc899 · outbound

This paper cites Flamingo: A visual language model for few-shot learning.Advances in neural information processing systems, 35: 23716–23736, 2022.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Flamingo: A visual language model for few-shot learning.Advances in neural information processing systems, 35: 23716–23736, 2022

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:40.625493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73716a63-e318-4c77-9738-337d9c2020a5 · outbound

This paper cites Hyperspectral target detection using self-supervised background learning.Advances in Space Research, 74(2):628–646, 2024.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Hyperspectral target detection using self-supervised background learning.Advances in Space Research, 74(2):628–646, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:40.750320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c085dd17-1f15-4749-bcc0-61541368d3e3 · outbound

This paper cites Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging.Nature Biomedical Engineering, 7(6):756–779, 2023.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging.Nature Biomedical Engineering, 7(6):756–779, 2023

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:40.884491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eae15a13-93c9-45df-84d3-d2489047da45 · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? BEiT: BERT Pre-Training of Image Transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:40.998040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc400826-bdad-426e-863a-519be6bc0539 · outbound

This paper cites VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.146060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75eb5ec4-e7f1-47d8-b1a7-62b7e2868c6b · outbound

This paper cites ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.245302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccbf8c50-6f53-4686-a02e-deedf42e885e · outbound

This paper cites Mixmatch: A holistic approach to semi-supervised learning.Advances in neural information processing systems, 32, 2019.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Mixmatch: A holistic approach to semi-supervised learning.Advances in neural information processing systems, 32, 2019

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.344929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdf3a6f2-ac4d-433e-88cc-07098f7c051d · outbound

This paper cites Unsupervised learning of visual features by contrasting cluster assignments.Advances in neural information processing systems, 33:9912–9924, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Unsupervised learning of visual features by contrasting cluster assignments.Advances in neural information processing systems, 33:9912–9924, 2020

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.430386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3782da5-f387-43d2-a4e4-9d5df1bf7fb1 · outbound

This paper cites Emerging properties in self-supervised vision transformers.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Emerging properties in self-supervised vision transformers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.567183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3c2e38f-0926-44b9-8504-063d9d348a57 · outbound

This paper cites A simple framework for contrastive learning of visual representations.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? A simple framework for contrastive learning of visual representations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.664468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7d0fc89-8b13-4612-a58d-9e97e2f1636b · outbound

This paper cites Big self-supervised models are strong semi-supervised learners.Advances in neural information processing systems, 33:22243–22255, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Big self-supervised models are strong semi-supervised learners.Advances in neural information processing systems, 33:22243–22255, 2020

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.782221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39bc9793-986c-4f80-bd57-b36e8816963d · outbound

This paper cites Exploring simple siamese representation learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Exploring simple siamese representation learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.891510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffdaa9d-fa1d-41d8-a4c6-3f75ba96d54a · outbound

This paper cites Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis.Medical image analysis, 54:280–296, 2019.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis.Medical image analysis, 54:280–296, 2019

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:41.988121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16eea5d2-7d11-4e78-8fed-2dfdc8c3e357 · outbound

This paper cites Orienting novel 3D objects using self-supervised learning of rotation transforms.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Orienting novel 3D objects using self-supervised learning of rotation transforms

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.063821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9027b8b-d548-4e93-9521-6e7dc1360d41 · outbound

This paper cites BERT: Pre-training of deep bidirectional transformers for language understanding.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? BERT: Pre-training of deep bidirectional transformers for language understanding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.186338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04388052-84bc-43a1-95d6-fc3554ac23df · outbound

This paper cites Unsupervised visual representation learning by context prediction.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Unsupervised visual representation learning by context prediction

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.254378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e59afc59-3600-4919-9a56-1ed362e9cc2f · outbound

This paper cites Self- supervised colorization towards monochrome-color camera systems using cycle cnn.IEEE Transactions on Image Processing, 30:6609–6622, 2021.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self- supervised colorization towards monochrome-color camera systems using cycle cnn.IEEE Transactions on Image Processing, 30:6609–6622, 2021

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.364242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d3e5796-69d3-40fb-854a-5ed61420e185 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.519185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4449698-704a-4d96-9589-27bc9b20d1af · outbound

This paper cites Everingham, L.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Everingham, L

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.605340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9884dc30-2d89-4b94-9b07-970dec39d438 · outbound

This paper cites The Pascal Visual Object Classes (VOC) Challenge.International Journal of Computer Vision, 88(2):303–338, 2010.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? The Pascal Visual Object Classes (VOC) Challenge.International Journal of Computer Vision, 88(2):303–338, 2010

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.717348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ae20ef1-cea9-414a-8ce0-1da4aeed6d2a · outbound

This paper cites Self-supervised representation learning by rotation feature decoupling.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervised representation learning by rotation feature decoupling

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.848986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d43ea98-2d20-45d7-969d-c88015334ff6 · outbound

This paper cites Bootstrap your own latent-a new approach to self-supervised learning.Advances in neural information processing systems, 33:21271–21284, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Bootstrap your own latent-a new approach to self-supervised learning.Advances in neural information processing systems, 33:21271–21284, 2020

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:42.963798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 722ceb76-1875-48ed-9436-08b524ff9f8b · outbound

This paper cites A survey on self-supervised learning: Algorithms, applications, and future trends.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):9052–9071, 2024.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? A survey on self-supervised learning: Algorithms, applications, and future trends.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):9052–9071, 2024

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.098235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c12c24-a931-4640-8325-ad6a5babe12b · outbound

This paper cites CrisisKAN: Knowledge- infused and explainable multimodal attention network for crisis event classification.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? CrisisKAN: Knowledge- infused and explainable multimodal attention network for crisis event classification

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.219852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fbb8446-71d9-402d-bed7-594812cccfb9 · outbound

This paper cites Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC).

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.330336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 699cf1fe-94a8-43b1-8843-91a44b3f6962 · outbound

This paper cites Deep residual learning for im- age recognition.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Deep residual learning for im- age recognition

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.435696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e14f0da7-79d8-4031-82b6-d9857ea74d56 · outbound

This paper cites Momentum contrast for unsupervised visual representation learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Momentum contrast for unsupervised visual representation learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.601371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acbf5561-e899-4f46-ba53-fba6508b51dd · outbound

This paper cites Masked autoencoders are scalable vision learners.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Masked autoencoders are scalable vision learners

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.650739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d5e7cc-f570-4f4d-a47d-9148d18b2574 · outbound

This paper cites Koniq-10k: An ecologically valid database for deep learning of blind image quality assessment.IEEE Transactions on Image Processing, 29:4041–4056, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Koniq-10k: An ecologically valid database for deep learning of blind image quality assessment.IEEE Transactions on Image Processing, 29:4041–4056, 2020

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.735728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c546e5-c28c-4ba4-be31-650ccb256255 · outbound

This paper cites Self-supervised learning by image colorization.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervised learning by image colorization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.842185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dfe544f-02b6-43d4-a17b-62f2ab1f0c50 · outbound

This paper cites Adco: Adversarial contrast for efficient learning of unsupervised representations from self-trained negative adversaries.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Adco: Adversarial contrast for efficient learning of unsupervised representations from self-trained negative adversaries

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:43.914053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2436833-be00-434e-90d3-98e7dd655ed0 · outbound

This paper cites Self-supervised color- concept association via image colorization.IEEE Transactions on Visualization and Computer Graphics, 29(1):247–256, 2022.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervised color- concept association via image colorization.IEEE Transactions on Visualization and Computer Graphics, 29(1):247–256, 2022

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.011571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f74a40e-2b05-40ff-97d7-aa8280872ab7 · outbound

This paper cites Self-supervised, semi-supervised, multi-context learning for the combined classification and segmentation of medical images.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervised, semi-supervised, multi-context learning for the combined classification and segmentation of medical images

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.048889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bcd5fff-5654-4f9f-ab6c-539ab8a55049 · outbound

This paper cites Scaling up visual and vision-language representation learning with noisy text supervision.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Scaling up visual and vision-language representation learning with noisy text supervision

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.160358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09af2bf8-0d83-493b-ad8c-10f83962a123 · outbound

This paper cites Self-supervised visual feature learning with deep neural networks: A survey.IEEE transactions on pattern analysis and machine intelligence, 43(11): 4037–4058, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervised visual feature learning with deep neural networks: A survey.IEEE transactions on pattern analysis and machine intelligence, 43(11): 4037–4058, 2020

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.244182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dd24910-049a-46d0-9d0e-3709767f9aae · outbound

This paper cites Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.350770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f74930-ed46-480c-a235-edb710a82936 · outbound

This paper cites Learning multiple layers of features from tiny images.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Learning multiple layers of features from tiny images

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.475403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca6a078-d1cc-4bfc-95b0-4326df54ca07 · outbound

This paper cites Temporal Ensembling for Semi-Supervised Learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Temporal Ensembling for Semi-Supervised Learning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.598216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff3a332-9d50-4b64-9f65-5923be830961 · outbound

This paper cites Hsieh, and Jang-Hwan Choi.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Hsieh, and Jang-Hwan Choi

Reference 42

Resolution: malformed identifier; no resolver link, observed 2026-08-02T05:58:44.703881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f43b941-e784-4f26-9b4f-a05a26a16b6a · outbound

This paper cites BLIP: Bootstrapping language- image pre-training for unified vision-language understanding and generation.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? BLIP: Bootstrapping language- image pre-training for unified vision-language understanding and generation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.737156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 971d9c6d-1d2d-4f5a-8510-8c9e62bcccd1 · outbound

This paper cites BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.827251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aed19a3c-5a14-4b7e-9c1c-dfb095384388 · outbound

This paper cites KADID-10k: A large-scale artificially distorted IQA database.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? KADID-10k: A large-scale artificially distorted IQA database

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.883804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab661813-795a-4f10-a264-3f1eb95fec14 · outbound

This paper cites Microsoft coco: Common objects in context.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Microsoft coco: Common objects in context

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:44.943555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11ef7f89-7d0a-49c6-a4a1-24a1448614aa · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.031401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4d12fac-30a9-4f21-930a-32ad7830080e · outbound

This paper cites Self-supervised learning: Generative or contrastive.IEEE transactions on knowledge and data engineering, 35(1):857–876, 2021.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervised learning: Generative or contrastive.IEEE transactions on knowledge and data engineering, 35(1):857–876, 2021

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.131889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6d0a56f-bef7-4639-b0a5-3ec67398aae0 · outbound

This paper cites Earthscape: A multi- modal dataset for surficial geologic mapping and earth surface analysis.arXiv preprint arXiv:2503.15625, 2025.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Earthscape: A multi- modal dataset for surficial geologic mapping and earth surface analysis.arXiv preprint arXiv:2503.15625, 2025

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.281259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e89f65d5-88bf-4c27-b1d8-2365464f0253 · outbound

This paper cites Damage identification in social media posts using multimodal deep learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Damage identification in social media posts using multimodal deep learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.409919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c55a7495-ad46-44ff-8d43-083a37a7f08e · outbound

This paper cites Self-supervision for medical image classification: State-of-the-art performance with ˜100 labeled training samples per class.Bioengineering, 10(8):895, 2023.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervision for medical image classification: State-of-the-art performance with ˜100 labeled training samples per class.Bioengineering, 10(8):895, 2023

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.584181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c81ba7b-006f-4ea0-8076-d59438d46d14 · outbound

This paper cites Unsupervised learning of visual representations by solving jigsaw puzzles.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Unsupervised learning of visual representations by solving jigsaw puzzles

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.684769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5511cfa4-0d96-4b4f-b651-8e5b0c66809b · outbound

This paper cites Real- istic evaluation of deep semi-supervised learning algorithms.Advances in neural information processing systems, 31, 2018.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Real- istic evaluation of deep semi-supervised learning algorithms.Advances in neural information processing systems, 31, 2018

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.797074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32efa712-a4c4-4b65-a856-d30ea9d3e616 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Representation Learning with Contrastive Predictive Coding

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.892308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10ab5ff1-b0e6-4986-b309-3a37a9f25bd3 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? DINOv2: Learning Robust Visual Features without Supervision

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:45.930892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 080963cc-3e33-4f17-bcc6-a4661fce2548 · outbound

This paper cites Self-supervised learning through colorization for microscopy images.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervised learning through colorization for microscopy images

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.005241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5b09be1-fd33-44ae-94b3-98ec5ed1600b · outbound

This paper cites Context encoders: Feature learning by inpainting.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Context encoders: Feature learning by inpainting

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.132024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d622989-8d6c-40f1-8343-3c5625a26091 · outbound

This paper cites Kosmos-2: Grounding Multimodal Large Language Models to the World.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Kosmos-2: Grounding Multimodal Large Language Models to the World

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.203541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ead4d0fe-e1a9-455f-8851-72283e4a00c2 · outbound

This paper cites Learning transferable visual models from natural language supervision.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Learning transferable visual models from natural language supervision

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.253937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec1dbb94-723a-49fb-8ae6-4280f5fda365 · outbound

This paper cites High- resolution image synthesis with latent diffusion models.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? High- resolution image synthesis with latent diffusion models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.345046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c471c8e9-4fc3-4ca5-8cc5-0dde0535fdb8 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? U-net: Convolutional networks for biomedical image segmentation

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.490853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8043861-2704-4160-9922-711bb63bfc26 · outbound

This paper cites an unresolved cited work.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Unresolved cited work

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.666281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cf0fbdf-633a-4c64-bceb-c242c763ae56 · outbound

This paper cites Fixmatch: Simplifying semi- supervised learning with consistency and confidence.Advances in neural information processing systems, 33:596–608, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Fixmatch: Simplifying semi- supervised learning with consistency and confidence.Advances in neural information processing systems, 33:596–608, 2020

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.798799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 511a14c4-5359-4efb-9109-027cbd732e55 · outbound

This paper cites an unresolved cited work.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Unresolved cited work

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:46.895433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac777ad1-065d-486a-b643-387c919ce046 · outbound

This paper cites What makes for good views for contrastive learning?Advances in neural information processing systems, 33:6827–6839, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? What makes for good views for contrastive learning?Advances in neural information processing systems, 33:6827–6839, 2020

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:47.023380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e52c98c-dd74-4aab-a43f-a0d9dd142309 · outbound

This paper cites YOLOv12: Attention-centric real-time object detectors.Advances in neural information processing systems, 38:78433–78457, 2025.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? YOLOv12: Attention-centric real-time object detectors.Advances in neural information processing systems, 38:78433–78457, 2025

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:47.154547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b60855a1-4370-4027-9a5e-d4805549f22c · outbound

This paper cites Real-time self-supervised achromatic face colorization.The Visual Computer, 39(12):6521–6536, 2023.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Real-time self-supervised achromatic face colorization.The Visual Computer, 39(12):6521–6536, 2023

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:47.267260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bf656eb-eb89-478f-a157-7ffd416eaf3d · outbound

This paper cites Toward a collective agenda on ai for earth science data analysis.IEEE Geoscience and Remote Sensing Magazine, 9(2):88–104, 2021.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Toward a collective agenda on ai for earth science data analysis.IEEE Geoscience and Remote Sensing Magazine, 9(2):88–104, 2021

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:47.423009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d63e8ab9-5aec-4d69-a75d-de6f93311cd1 · outbound

This paper cites A survey on semi-supervised learning.Machine learning, 109(2):373–440, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? A survey on semi-supervised learning.Machine learning, 109(2):373–440, 2020

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:47.598960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68b63625-a5d8-4bb0-b327-5ae87fbc20e7 · outbound

This paper cites Optimizing area under the roc curve using semi-supervised learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Optimizing area under the roc curve using semi-supervised learning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:47.731995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df41f95c-aeb5-4acb-9780-74debd35deb0 · outbound

This paper cites Unsupervised learning of visual representations using videos.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Unsupervised learning of visual representations using videos

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:47.889328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c15dbe6-33df-4295-9bda-d51023ed6579 · outbound

This paper cites Unsupervised data aug- mentation for consistency training.Advances in neural information processing systems, 33: 6256–6268, 2020.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Unsupervised data aug- mentation for consistency training.Advances in neural information processing systems, 33: 6256–6268, 2020

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:47.997734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f7a6ad4-2e9b-473d-8791-d59d3c825227 · outbound

This paper cites Simmim: A simple framework for masked image modeling.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Simmim: A simple framework for masked image modeling

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:48.180701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6414584d-b630-4a1d-98fc-cd07838aae9b · outbound

This paper cites Image enhanced rotation prediction for self-supervised learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Image enhanced rotation prediction for self-supervised learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:48.273513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dbf9192-8061-4236-900e-04ea95d8fecf · outbound

This paper cites Self-supervised 3d action representation learning with skeleton cloud colorization.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(1):509–524, 2023.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Self-supervised 3d action representation learning with skeleton cloud colorization.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(1):509–524, 2023

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:48.348391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation babb9b42-5912-4f8a-b345-19005b16bd1e · outbound

This paper cites Barlow twins: Self- supervised learning via redundancy reduction.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Barlow twins: Self- supervised learning via redundancy reduction

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:48.480576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a005fdfd-3faa-4adb-bd71-c8d867257f48 · outbound

This paper cites S4L: Self-supervised semi-supervised learning.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? S4L: Self-supervised semi-supervised learning

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:48.570716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46752f6c-d181-48b6-8e5b-80ec5ffff29e · outbound

This paper cites Colorful image colorization.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Colorful image colorization

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:48.701453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f453bf6-9e27-4425-ae54-b5a4ce7f37c9 · outbound

This paper cites Combining self-supervised and supervised learning with noisy labels.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Combining self-supervised and supervised learning with noisy labels

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:48.794228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 289fe9be-bd3d-4dc9-be26-5ecf85ed6acf · outbound

This paper cites iBOT: Image BERT Pre-Training with Online Tokenizer.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? iBOT: Image BERT Pre-Training with Online Tokenizer

Reference 80

Resolution: malformed identifier; no resolver link, observed 2026-08-02T05:58:48.847518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c21a95f-2874-4075-b6fa-8eb8c5ac42d7 · outbound

This paper cites 2|X∩Y| |X|+|Y| .(3).

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? 2|X∩Y| |X|+|Y| .(3)

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:49.004451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e520be53-930b-4b45-b6c6-ddc8cf6de573 · outbound

This paper cites IoU, also called the Jaccard index, measures the average overlap between predicted masks and the ground truth.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? IoU, also called the Jaccard index, measures the average overlap between predicted masks and the ground truth

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:49.154602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e91f8fbf-3ce5-44ab-b56a-7f1c80006c25 · outbound

This paper cites P= T P T P+F P.(5) 2.Recall:Also called sensitivity, this metric measures how many of the actual positive cases were correctly identified by the model.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? P= T P T P+F P.(5) 2.Recall:Also called sensitivity, this metric measures how many of the actual positive cases were correctly identified by the model

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:49.256983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0adb1e97-1854-4d5e-9e8a-cf823be1a113 · outbound

This paper cites It is computed as the mean of the Average Precision (AP) overNclasses: mAP= 1 N NX i=1 APi,(7) where APi denotes the AP for class i.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? It is computed as the mean of the Average Precision (AP) overNclasses: mAP= 1 N NX i=1 APi,(7) where APi denotes the AP for class i

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:49.371420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11652693-e6d4-4df2-9da9-cf9f9f464b16 · outbound

This paper cites SROCC= 1− 6 Pn i=1 d2 i n(n2 −1) ,(9) whered i is is the difference between the ranks ofy i andˆy.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? SROCC= 1− 6 Pn i=1 d2 i n(n2 −1) ,(9) whered i is is the difference between the ranks ofy i andˆy

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:49.470588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8702adf4-eee4-4606-8874-a7b34ee089fc · outbound

This paper cites an unresolved cited work.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? Unresolved cited work

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-02T05:58:49.654052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43e70c49-9caf-4759-994a-9058b11df072 · outbound

This paper cites 22 Table 3: Classification performance of different SSL frameworks on CrisisMMD using 128 ×128 image inputs under the PFT and JT training paradigms with 100% labeled data.

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? 22 Table 3: Classification performance of different SSL frameworks on CrisisMMD using 128 ×128 image inputs under the PFT and JT training paradigms with 100% labeled data

Reference 87

Resolution: malformed identifier; no resolver link, observed 2026-08-02T05:58:49.782338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers