{"total":116,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021,"area":"inference"},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133,"area":null},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91,"area":"mllm"},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85,"area":null},{"id":"2208.06049","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","created":"2022-08-11","cited_by_count":69,"area":null},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68,"area":null},{"id":"2403.10701","title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","created":"2024-03-15","cited_by_count":64,"area":null},{"id":"2305.17328","title":"Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers","created":"2023-05-27","cited_by_count":62,"area":"inference"},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"area":null},{"id":"2304.07213","title":"Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar","created":"2023-04-14","cited_by_count":60,"area":null},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2401.04350","title":"Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness","created":"2024-01-09","cited_by_count":48,"area":"mllm"},{"id":"2204.03359","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","created":"2022-04-07","cited_by_count":37,"area":null},{"id":"2304.00287","title":"Vision Transformers with Mixed-Resolution Tokenization","created":"2023-04-01","cited_by_count":36,"area":null},{"id":"2304.05884","title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","created":"2023-04-12","cited_by_count":36,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2302.11874","title":"What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers","created":"2023-02-23","cited_by_count":35,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","cited_by_count":33,"area":null},{"id":"2211.09807","title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","created":"2022-11-17","cited_by_count":31,"area":null},{"id":"2302.11893","title":"A framework for benchmarking class-out-of-distribution detection and its application to ImageNet","created":"2023-02-23","cited_by_count":31,"area":null},{"id":"2301.02241","title":"CiT: Curation in Training for Effective Vision-Language Data","created":"2023-01-05","cited_by_count":27,"area":"mllm"},{"id":"2210.00788","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","created":"2022-10-03","cited_by_count":25,"area":null},{"id":"2211.09799","title":"CAE v2: Context Autoencoder with CLIP Target","created":"2022-11-17","cited_by_count":25,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2402.18853","title":"Rethinking Multi-domain Generalization with A General Learning Objective","created":"2024-02-29","cited_by_count":23,"area":null},{"id":"2402.10093","title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","created":"2024-02-15","cited_by_count":19,"area":null},{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18,"area":null},{"id":"2212.06254","title":"You Only Need a Good Embeddings Extractor to Fix Spurious Correlations","created":"2022-12-12","cited_by_count":17,"area":null},{"id":"2303.15443","title":"GeoNet: Benchmarking Unsupervised Adaptation across Geographies","created":"2023-03-27","cited_by_count":17,"area":null},{"id":"2405.04457","title":"Towards Geographic Inclusion in the Evaluation of Text-to-Image Models","created":"2024-05-07","cited_by_count":16,"area":null},{"id":"2312.01280","title":"Brain Decodes Deep Nets","created":"2023-12-03","cited_by_count":14,"area":null},{"id":"2406.07236","title":"Let Go of Your Labels with Unsupervised Transfer","created":"2024-06-11","cited_by_count":14,"area":"mllm"},{"id":"2407.17331","title":"Multi-label Cluster Discrimination for Visual Representation Learning","created":"2024-07-24","cited_by_count":14,"area":null},{"id":"2207.08034","title":"Progress and limitations of deep networks to recognize objects in unusual poses","created":"2022-07-16","cited_by_count":13,"area":null},{"id":"2302.01381","title":"Effective Robustness against Natural Distribution Shifts for Models with Different Training Data","created":"2023-02-02","cited_by_count":13,"area":null},{"id":"2308.14597","title":"Adversarial Attacks on Foundational Vision Models","created":"2023-08-28","cited_by_count":13,"area":null},{"id":"2407.11717","title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2409.11923","title":"Agglomerative Token Clustering","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2310.11031","title":"Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2312.07408","title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models","created":"2023-12-12","cited_by_count":11,"area":"mllm"},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2305.17023","title":"Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2305.19402","title":"Contextual Vision Transformers for Robust Representation Learning","created":"2023-05-30","cited_by_count":10,"area":null},{"id":"2312.02364","title":"Class-Discriminative Attention Maps for Vision Transformers","created":"2023-12-04","cited_by_count":10,"area":null},{"id":"2404.15653","title":"CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data","created":"2024-04-24","cited_by_count":10,"area":null},{"id":"2412.11521","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","created":"2024-12-16","cited_by_count":10,"area":null},{"id":"2205.10144","title":"The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks","created":"2022-05-20","cited_by_count":9,"area":null},{"id":"2302.01497","title":"Gradient Estimation for Unseen Domain Risk Minimization with Pre-Trained Models","created":"2023-02-03","cited_by_count":9,"area":null},{"id":"2307.10586","title":"A Holistic Assessment of the Reliability of Machine Learning Systems","created":"2023-07-20","cited_by_count":9,"area":null},{"id":"2308.06198","title":"DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity","created":"2023-08-11","cited_by_count":9,"area":null},{"id":"2312.11473","title":"Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion Models","created":"2023-11-24","cited_by_count":9,"area":"diffusion"},{"id":"2403.16020","title":"PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference","created":"2024-03-24","cited_by_count":9,"area":null},{"id":"2406.07543","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2412.02856","title":"Is Large-Scale Pretraining the Secret to Good Domain Generalization?","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2303.11114","title":"SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage","created":"2023-03-20","cited_by_count":8,"area":null},{"id":"2301.07836","title":"Masked Autoencoding Does Not Help Natural Language Supervision at Scale","created":"2023-01-19","cited_by_count":7,"area":null},{"id":"2306.07952","title":"MOFI: Learning Image Representations from Noisy Entity Annotated Images","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2402.03973","title":"A comparison between humans and AI at recognizing objects in unusual poses","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2408.07832","title":"LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers","created":"2024-07-31","cited_by_count":7,"area":null},{"id":"2503.04852","title":"CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data","created":"2025-03-06","cited_by_count":7,"area":null},{"id":"2304.05391","title":"Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2406.11422","title":"Cross-domain Open-world Discovery","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2409.14205","title":"Egocentric zone-aware action recognition across environments","created":"2024-09-21","cited_by_count":6,"area":null},{"id":"2409.15264","title":"UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework","created":"2024-09-23","cited_by_count":6,"area":null},{"id":"2210.03150","title":"Towards Out-of-Distribution Adversarial Robustness","created":"2022-10-06","cited_by_count":5,"area":null},{"id":"2302.08572","title":"Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers","created":"2023-02-16","cited_by_count":5,"area":null},{"id":"2303.01233","title":"Domain-aware Triplet loss in Domain Generalization","created":"2023-03-01","cited_by_count":5,"area":null},{"id":"2310.10008","title":"Towards Unified and Effective Domain Generalization","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2311.11293","title":"From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web","created":"2023-11-19","cited_by_count":5,"area":null},{"id":"2312.14149","title":"TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification","created":"2023-12-21","cited_by_count":5,"area":"mllm"},{"id":"2312.17473","title":"FerKD: Surgical Label Adaptation for Efficient Distillation","created":"2023-12-29","cited_by_count":5,"area":"distill"},{"id":"2505.17883","title":"FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2505.18886","title":"KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2507.10894","title":"NavComposer: Composing Language Instructions for Navigation Trajectories through Action-Scene-Object Modularization","created":"2025-07-15","cited_by_count":5,"area":null},{"id":"2305.05208","title":"Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data","created":"2023-05-09","cited_by_count":4,"area":null},{"id":"2311.15200","title":"SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification","created":"2023-11-26","cited_by_count":4,"area":null},{"id":"2403.05535","title":"Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos","created":"2024-03-08","cited_by_count":4,"area":null},{"id":"2408.17062","title":"Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer","created":"2024-08-30","cited_by_count":4,"area":"inference"},{"id":"2504.20902","title":"Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers","created":"2025-04-29","cited_by_count":4,"area":null},{"id":"2505.18930","title":"WeedNet: A Foundation Model-Based Global-to-Local AI Approach for Real-Time Weed Species Identification and Classification","created":"2025-05-25","cited_by_count":4,"area":null},{"id":"2303.16887","title":"Towards Understanding the Effect of Pretraining Label Granularity","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2305.14521","title":"Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2308.14753","title":"Efficient Discovery and Effective Evaluation of Visual Perceptual Similarity: A Benchmark and Beyond","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2311.11396","title":"Towards interpretable-by-design deep learning algorithms","created":"2023-11-19","cited_by_count":3,"area":null},{"id":"2410.20631","title":"PViT: Prior-augmented Vision Transformer for Out-of-distribution Detection","created":"2024-10-27","cited_by_count":3,"area":null},{"id":"2401.08469","title":"Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training","created":"2024-01-16","cited_by_count":2,"area":null},{"id":"2406.08039","title":"Differentially Private Prototypes for Imbalanced Transfer Learning","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2409.02792","title":"UnLearning from Experience to Avoid Spurious Correlations","created":"2024-09-04","cited_by_count":2,"area":"safety"},{"id":"2510.18228","title":"Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2510.24105","title":"Enhancing Pre-trained Representation Classifiability can Boost its Interpretability","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2510.27584","title":"Image Hashing via Cross-View Code Alignment in the Age of Foundation Models","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2603.03969","title":"Scaling Dense Event-Stream Pretraining from Visual Foundation Models","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2312.10105","title":"SeiT++: Masked Token Modeling Improves Storage-efficient Training","created":"2023-12-15","cited_by_count":1,"area":null}],"next_cursor":"100"}