Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models | Paper Citation Record

Observation 942359d4-a5dc-4686-b4e7-26be0d0b1091 · outbound

This paper cites Blended latent diffusion.ACM transactions on graphics (TOG), 42 (4):1–11, 2023.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Blended latent diffusion.ACM transactions on graphics (TOG), 42 (4):1–11, 2023

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.486965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e96677ad-e6de-47fa-9e26-14a68b1349bf · outbound

This paper cites Flux.1 fill [dev].

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Flux.1 fill [dev]

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.514272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 295ef5f2-14d5-4fb0-a01e-4a368bf8cf4f · outbound

This paper cites The cityscapes dataset for semantic urban scene understanding.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models The cityscapes dataset for semantic urban scene understanding

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.457053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c7fa831e-8ef3-4de1-989d-e9208ca07657 · outbound

This paper cites Class-balanced loss based on effective number of samples.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Class-balanced loss based on effective number of samples

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.493091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c2c1c9b3-e35a-40c2-9541-7e73d54eea1a · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models An image is worth 16x16 words: Transformers for image recognition at scale

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.499417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2c46a83c-0db1-4e38-abde-913b6731f6fb · outbound

This paper cites Active learning by labeling features.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Active learning by labeling features

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.466412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 978f4933-e506-48b2-8308-3e096403499f · outbound

This paper cites Data augmentation for object detec- tion via controllable diffusion models.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Data augmentation for object detec- tion via controllable diffusion models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.470638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 13a91515-3f4b-4b0a-86e6-271c216da455 · outbound

This paper cites an unresolved cited work.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-07-06T21:32:56.464074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 90e35923-b866-4e35-bebf-9d1c5de2ac12 · outbound

This paper cites Dropout as a bayesian approximation: Representing model uncertainty in deep learning.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Dropout as a bayesian approximation: Representing model uncertainty in deep learning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.459383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e43ec385-2702-4d3e-9fe9-ef160f1f60ca · outbound

This paper cites Deep bayesian active learning with image data.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Deep bayesian active learning with image data

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.510129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8ec1b2b0-9d86-461b-aa57-77873cd30704 · outbound

This paper cites Denoising dif- fusion probabilistic models.Advances in neural information processing systems, 33:6840–6851.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Denoising dif- fusion probabilistic models.Advances in neural information processing systems, 33:6840–6851

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.451610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c50cd004-6a0f-495a-9109-b10de59bfeca · outbound

This paper cites Diffusemix: Label- preserving data augmentation with diffusion models.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Diffusemix: Label- preserving data augmentation with diffusion models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.454776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 28c52d51-256d-43c6-b09f-037076516d6b · outbound

This paper cites Computer vision for autonomous vehicles: Prob- lems, datasets and state of the art.Foundations and Trends in Computer Graphics and Vision, 12(1-3):1–308, 2020.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Computer vision for autonomous vehicles: Prob- lems, datasets and state of the art.Foundations and Trends in Computer Graphics and Vision, 12(1-3):1–308, 2020

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.440642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a096a28f-00a4-4a82-8ed0-a934bfb33059 · outbound

This paper cites Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T10:25:41.629046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 069ef3a2-a286-470b-b666-84ad8de0aee8 · outbound

This paper cites Dataset enhancement with instance-level augmentations.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Dataset enhancement with instance-level augmentations

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.436419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation db1d3ce5-f25d-45c7-8b2e-5ed87baaf048 · outbound

This paper cites Tracer: Extreme attention guided salient object tracing network (stu- dent abstract).

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Tracer: Extreme attention guided salient object tracing network (stu- dent abstract)

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.428166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f4d9e797-2a1b-4be6-af81-2c629e1c2297 · outbound

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

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.434142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 582b883f-c547-43b4-b547-2e6f52ec594a · outbound

This paper cites A simple background augmentation method for object detection with diffusion model.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models A simple background augmentation method for object detection with diffusion model

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.412842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7de05d22-507c-4d96-94c2-d48cbbdf1c99 · outbound

This paper cites Focal loss for dense object detection.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Focal loss for dense object detection

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.472555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation befa1b6f-6927-4b73-96b7-7228e2663b84 · outbound

This paper cites Decoupled weight decay regularization.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Decoupled weight decay regularization

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.443226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a658c0d0-4c8c-4bfc-a498-ad281ee81439 · outbound

This paper cites Repaint: Inpainting using denoising diffusion probabilistic models.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Repaint: Inpainting using denoising diffusion probabilistic models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.410525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8eb2cc59-4782-4e58-8b5a-e1d75f47bf39 · outbound

This paper cites Uavid: A semantic segmentation dataset for uav imagery.ISPRS journal of photogrammetry and remote sensing, 165:108–119, 2020.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Uavid: A semantic segmentation dataset for uav imagery.ISPRS journal of photogrammetry and remote sensing, 165:108–119, 2020

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.478430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1f799cef-72e7-4505-8ffe-1381bfa7c5fe · outbound

This paper cites CEREALS - cost- effective region-based active learning for semantic segmen- 9 tation.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models CEREALS - cost- effective region-based active learning for semantic segmen- 9 tation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.482960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 413b9e11-2abb-476b-bcb9-aee4bb9ec9fa · outbound

This paper cites Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation.Advances in Neural Information Processing Systems, 36:76872–76892, 2023.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation.Advances in Neural Information Processing Systems, 36:76872–76892, 2023

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.468613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cf8bd2db-a759-4958-a718-7663ca8945a4 · outbound

This paper cites Uncertainty-aware controlnet: Bridging domain gaps with synthetic image generation.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Uncertainty-aware controlnet: Bridging domain gaps with synthetic image generation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.474759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9eaf119d-e5c9-4061-9fec-2c6d402a80e7 · outbound

This paper cites an unresolved cited work.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-07-06T21:32:56.448272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f594b937-1474-469d-8436-6a5d0ca6de7a · outbound

This paper cites Scalable diffusion models with transformers.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Scalable diffusion models with transformers

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.445529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7cecbb93-f0ad-4dd1-b042-bef0256bb668 · outbound

This paper cites Sdxl: Improving latent diffusion models for high-resolution image synthesis.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Sdxl: Improving latent diffusion models for high-resolution image synthesis

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.431225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a8efbc24-da02-4954-9c75-607e13b62402 · outbound

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

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models High-resolution image synthesis with latent diffusion models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.484931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation baff80fd-8db6-489a-8ae5-6c9a92f84c8d · outbound

This paper cites Training region-based object detectors with online hard ex- ample mining.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Training region-based object detectors with online hard ex- ample mining

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.461487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1bd9ff57-80bf-4bff-84a2-95b9748ac0d8 · outbound

This paper cites Effective data augmentation with diffusion models.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Effective data augmentation with diffusion models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.419715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bce0d741-911e-4295-8de2-1f766db2ec47 · outbound

This paper cites Datasetdm: Synthesizing data with perception annota- tions using diffusion models.Advances in Neural Informa- tion Processing Systems, 36:54683–54695, 2023.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Datasetdm: Synthesizing data with perception annota- tions using diffusion models.Advances in Neural Informa- tion Processing Systems, 36:54683–54695, 2023

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.423867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 68d6e1a6-aa0e-47e1-bdff-f583beb3fe95 · outbound

This paper cites Diffumask: Synthesizing images with pixel-level annotations for semantic segmentation using dif- fusion models.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Diffumask: Synthesizing images with pixel-level annotations for semantic segmentation using dif- fusion models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.505805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9e73befe-885f-49d0-92e3-4373f3ef87cd · outbound

This paper cites Segformer: Simple and efficient design for semantic segmentation with transform- ers.Advances in neural information processing systems, 34: 12077–12090.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Segformer: Simple and efficient design for semantic segmentation with transform- ers.Advances in neural information processing systems, 34: 12077–12090

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.507986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 02e6262b-39f8-43d3-b410-f0195bc43cd6 · outbound

This paper cites Freemask: Synthetic images with dense annotations make stronger segmentation models.Advances in Neural Information Processing Systems, 36:18659–18675,.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Freemask: Synthetic images with dense annotations make stronger segmentation models.Advances in Neural Information Processing Systems, 36:18659–18675,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.501592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9dfa500c-4ef1-42b6-b071-c52fd146e5f3 · outbound

This paper cites Learning loss for ac- tive learning.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Learning loss for ac- tive learning

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.416190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1a387c71-0188-421f-8b28-1871ee4272b8 · outbound

This paper cites Bdd100k: A diverse driving dataset for heterogeneous multitask learning.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Bdd100k: A diverse driving dataset for heterogeneous multitask learning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.503747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1fdaaad7-e913-4507-8939-0f3aa2a469df · outbound

This paper cites Adding conditional control to text-to-image diffusion models.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Adding conditional control to text-to-image diffusion models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.495199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5429818c-063f-4459-9f69-cb62e5125b62 · outbound

This paper cites X-paste: Revisiting scalable copy-paste for instance segmentation us- ing CLIP and StableDiffusion.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models X-paste: Revisiting scalable copy-paste for instance segmentation us- ing CLIP and StableDiffusion

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.497304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0ea9e758-ae00-42b3-b232-bd6453fe35b5 · outbound

This paper cites Recon: Region-controllable data augmentation with rectification and alignment for object detection.Advances in Neural Information Processing Systems, 38:74897–74926,.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models Recon: Region-controllable data augmentation with rectification and alignment for object detection.Advances in Neural Information Processing Systems, 38:74897–74926,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.489063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 08190e54-c583-452b-82f4-c2081ec1a806 · outbound

This paper cites The columns show the original image, the predictive-entropy map, the preserved uncertain region, and the final augmented image after inpainting and paste-back.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models The columns show the original image, the predictive-entropy map, the preserved uncertain region, and the final augmented image after inpainting and paste-back

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.480889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2621dd72-d9d4-4829-a94a-b118499f835d · outbound

This paper cites photorealistic, ultra-detailed, 4K high- resolution, sharp focus, high quality, in the style of the Cityscapes dataset.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models photorealistic, ultra-detailed, 4K high- resolution, sharp focus, high quality, in the style of the Cityscapes dataset

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.491098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f4b158c2-63dd-46f3-ad0f-6c960274fee5 · outbound

This paper cites To apply this to densely labeled semantic segmentation use-cases like Cityscapes [3], we assign each semantic class to either fore- ground or background.

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models To apply this to densely labeled semantic segmentation use-cases like Cityscapes [3], we assign each semantic class to either fore- ground or background

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T21:32:56.512277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers