CanViT is the first task- and policy-agnostic AVFM pretrained via passive-to-active dense latent distillation on 13.2M scenes and 1B random glimpses, achieving 38.5% ADE20K mIoU in one glimpse and 84.5% ImageNet-1k top-1 after fine-tuning.
hub
Imagenet-21k pretraining for the masses
21 Pith papers cite this work, alongside 4 external citations. Polarity classification is still indexing.
21
Pith papers citing it
4
external citations · external index
hub tools
citation-role summary
dataset 2
method 1
citation-polarity summary
representative citing papers
CIM directly aligns data distributions to condense large-scale datasets with minimal information loss, achieving new SOTA results on ImageNet-1K distillation at IPC=10.
CPF-GCD enforces low-rank compositional structure on vision backbone features via spatial primitive fields so that novel categories emerge as new activation patterns over a shared vocabulary of reusable visual primitives.
EGIDE provides 149,215 edge-on galaxy candidates from DESI DR10 with homogeneous photometry, masses, and redshifts, ten times larger than EGIPS.
ExDet proposes a lightweight framework using text-guided extrapolation, detector-compatible rectification, and recalibrated proposals to achieve state-of-the-art open-domain open-vocabulary detection on multiple benchmarks.
VISReg replaces covariance in VICReg-style objectives with sliced-Wasserstein sketching for JEPA training, claiming better OOD performance and resilience to collapse.
The authors define the LV-OSD problem and introduce the LVDor dual-branch framework with TPDW dynamic weighting and PRM masking to align multimodal prompts for open-set detection.
E²-LoRA structures low-rank adaptations by energy concentration and ordering with dynamic rank allocation to achieve state-of-the-art continual learning.
WePE encodes 2D patch positions in Vision Transformers via Weierstrass elliptic functions on the complex plane to exploit double periodicity and derive relative positions algebraically.
Exploiting linear structure in VLM embeddings, a synthetic-data pre-training method yields background-invariant representations that exceed 90% worst-group accuracy on Waterbirds even under 100% spurious correlation with no minority examples in training.
Adapting vision foundation models with LoRA and kurtosis-guided unsupervised test-time adaptation matches or exceeds domain-specific models for seismic denoising across multiple sites and unseen data.
Using contrastive examples with vision-language models and a new CLIP-based scoring method called CSP produces more faithful and granular neuron labels than prior activation-only approaches.
StableTTA improves ImageNet-1K accuracy across 71 vision models by stabilizing logit aggregation under coherent-batch inference and enabling efficient single-forward-pass adaptation.
MePo refines pretrained backbones via meta-learning on constructed pseudo tasks and initializes a meta covariance matrix to enable robust second-order alignment, yielding 12-15% gains on CIFAR-100, ImageNet-R and CUB-200 in rehearsal-free GCL settings.
Fine-tuned image classifiers, led by RegNetY-16GF at about 99% top-1 accuracy, can sort historical archaeological page scans into 11 content categories, and the authors release the dataset, code, and model weights.
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
JetViT uses post-training attention search to hybridize full-attention ViTs with linear and window attention blocks, achieving up to 1.79x throughput gains on high-res images while preserving accuracy on DINOv3 and DepthAnythingV2.
MobileVLM achieves on-par performance with much larger vision-language models on standard benchmarks while delivering state-of-the-art inference speeds of 21.5 tokens per second on Snapdragon 888 CPU and 65.3 on Jetson Orin GPU.
Fine-tuned RegNetY-16GF reaches 99.16% accuracy classifying 48k century-old Czech archival pages into 11 visual content types, beating a 75% hand-crafted feature baseline, with models and data released publicly.
HandyLabel enables real-time data annotation by mapping hand gestures to labels, with ResNet50 on skeleton-preprocessed HaGRID data reaching 0.923 F1-score and 88.9% of 46 study participants preferring it to traditional post-processing tools.
The report overviews five maritime computer vision benchmark challenges, their datasets, protocols, quantitative results, and top team approaches from the MaCVi 2026 workshop.
citing papers explorer
-
CanViT: Toward Active-Vision Foundation Models
CanViT is the first task- and policy-agnostic AVFM pretrained via passive-to-active dense latent distillation on 13.2M scenes and 1B random glimpses, achieving 38.5% ADE20K mIoU in one glimpse and 84.5% ImageNet-1k top-1 after fine-tuning.
-
Condensing Large-Scale Datasets Directly with Minimal Information Loss
CIM directly aligns data distributions to condense large-scale datasets with minimal information loss, achieving new SOTA results on ImageNet-1K distillation at IPC=10.
-
Identifying Latent Concepts and Structures for Generalized Category Discovery
CPF-GCD enforces low-rank compositional structure on vision backbone features via spatial primitive fields so that novel categories emerge as new activation patterns over a shared vocabulary of reusable visual primitives.
-
The Edge-on Galaxies in the DESI survey (EGIDE): sample building and photometry
EGIDE provides 149,215 edge-on galaxy candidates from DESI DR10 with homogeneous photometry, masses, and redshifts, ten times larger than EGIPS.
-
ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification
ExDet proposes a lightweight framework using text-guided extrapolation, detector-compatible rectification, and recalibrated proposals to achieve state-of-the-art open-domain open-vocabulary detection on multiple benchmarks.
-
VISReg: Variance-Invariance-Sketching Regularization for JEPA training
VISReg replaces covariance in VICReg-style objectives with sliced-Wasserstein sketching for JEPA training, claiming better OOD performance and resilience to collapse.
-
LV-OSD: Language-Vision-Complementary Open-Set Object Detection
The authors define the LV-OSD problem and introduce the LVDor dual-branch framework with TPDW dynamic weighting and PRM masking to align multimodal prompts for open-set detection.
-
Energy-Structured Low-Rank Adaptation for Continual Learning
E²-LoRA structures low-rank adaptations by energy concentration and ordering with dynamic rank allocation to achieve state-of-the-art continual learning.
-
Weierstrass Positional Encoding for Vision Transformers
WePE encodes 2D patch positions in Vision Transformers via Weierstrass elliptic functions on the complex plane to exploit double periodicity and derive relative positions algebraically.
-
Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs
Exploiting linear structure in VLM embeddings, a synthetic-data pre-training method yields background-invariant representations that exceed 90% worst-group accuracy on Waterbirds even under 100% spurious correlation with no minority examples in training.
-
Parameter-Efficient Adaptation of Pre-Trained Vision Foundation Models for Active and Passive Seismic Data Denoising
Adapting vision foundation models with LoRA and kurtosis-guided unsupervised test-time adaptation matches or exceeds domain-specific models for seismic denoising across multiple sites and unseen data.
-
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
Using contrastive examples with vision-language models and a new CLIP-based scoring method called CSP produces more faithful and granular neuron labels than prior activation-only approaches.
-
StableTTA: Improving Vision Model Performance by Training-free Test-Time Adaptation Methods
StableTTA improves ImageNet-1K accuracy across 71 vision models by stabilizing logit aggregation under coherent-batch inference and enabling efficient single-forward-pass adaptation.
-
MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
MePo refines pretrained backbones via meta-learning on constructed pseudo tasks and initializes a meta covariance matrix to enable robust second-order alignment, yielding 12-15% gains on CIFAR-100, ImageNet-R and CUB-200 in rehearsal-free GCL settings.
-
Page image classification for content-specific data processing
Fine-tuned image classifiers, led by RegNetY-16GF at about 99% top-1 accuracy, can sort historical archaeological page scans into 11 content categories, and the authors release the dataset, code, and model weights.
-
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
-
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
JetViT uses post-training attention search to hybridize full-attention ViTs with linear and window attention blocks, achieving up to 1.79x throughput gains on high-res images while preserving accuracy on DINOv3 and DepthAnythingV2.
-
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
MobileVLM achieves on-par performance with much larger vision-language models on standard benchmarks while delivering state-of-the-art inference speeds of 21.5 tokens per second on Snapdragon 888 CPU and 65.3 on Jetson Orin GPU.
-
Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing
Fine-tuned RegNetY-16GF reaches 99.16% accuracy classifying 48k century-old Czech archival pages into 11 visual content types, beating a 75% hand-crafted feature baseline, with models and data released publicly.
-
HandyLabel: Towards Post-Processing to Real-Time Annotation Using Skeleton Based Hand Gesture Recognition
HandyLabel enables real-time data annotation by mapping hand gestures to labels, with ResNet50 on skeleton-preprocessed HaGRID data reaching 0.923 F1-score and 88.9% of 46 study participants preferring it to traditional post-processing tools.
-
4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview
The report overviews five maritime computer vision benchmark challenges, their datasets, protocols, quantitative results, and top team approaches from the MaCVi 2026 workshop.