{"total":208,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864,"area":null},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616,"area":null},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592,"area":null},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368,"area":null},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291,"area":null},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279,"area":null},{"id":"2103.04098","title":"WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition","created":"2021-03-06","cited_by_count":223,"area":null},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185,"area":null},{"id":"2106.05095","title":"ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation","created":"2021-06-09","cited_by_count":184,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2103.05073","title":"Offboard 3D Object Detection from Point Cloud Sequences","created":"2021-03-08","cited_by_count":145,"area":null},{"id":"2106.05304","title":"Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline","created":"2021-06-09","cited_by_count":145,"area":null},{"id":"2110.10832","title":"Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization","created":"2021-10-21","cited_by_count":144,"area":null},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118,"area":null},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116,"area":null},{"id":"2103.15670","title":"On the Adversarial Robustness of Vision Transformers","created":"2021-03-29","cited_by_count":106,"area":null},{"id":"2108.11353","title":"Multi-Task Self-Training for Learning General Representations","created":"2021-08-25","cited_by_count":85,"area":null},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82,"area":null},{"id":"2103.13646","title":"Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels","created":"2021-03-25","cited_by_count":69,"area":null},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61,"area":null},{"id":"2205.00329","title":"Continual Learning with Foundation Models: An Empirical Study of Latent Replay","created":"2022-04-30","cited_by_count":61,"area":null},{"id":"2209.03942","title":"Data Feedback Loops: Model-driven Amplification of Dataset Biases","created":"2022-09-08","cited_by_count":60,"area":null},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2211.04533","title":"Harmonizing the object recognition strategies of deep neural networks with humans","created":"2022-11-08","cited_by_count":59,"area":null},{"id":"2110.02797","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","created":"2021-10-06","cited_by_count":57,"area":null},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57,"area":null},{"id":"2104.09376","title":"Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training","created":"2021-04-19","cited_by_count":54,"area":null},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2208.11296","title":"Semi-Supervised and Unsupervised Deep Visual Learning: A Survey","created":"2022-08-24","cited_by_count":52,"area":null},{"id":"2106.05682","title":"DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2106.07807","title":"Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data","created":"2021-06-14","cited_by_count":50,"area":null},{"id":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50,"area":null},{"id":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49,"area":null},{"id":"2112.01001","title":"SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency","created":"2021-12-02","cited_by_count":48,"area":null},{"id":"2205.10334","title":"UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation","created":"2022-05-20","cited_by_count":45,"area":null},{"id":"2106.11118","title":"SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving","created":"2021-06-21","cited_by_count":43,"area":null},{"id":"2204.10149","title":"WebFace260M: A Benchmark for Million-Scale Deep Face Recognition","created":"2022-04-21","cited_by_count":42,"area":null},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41,"area":null},{"id":"2202.01747","title":"The Met Dataset: Instance-level Recognition for Artworks","created":"2022-02-03","cited_by_count":40,"area":null},{"id":"2101.05913","title":"Supervised Transfer Learning at Scale for Medical Imaging","created":"2021-01-14","cited_by_count":38,"area":null},{"id":"2103.13990","title":"More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval","created":"2021-03-25","cited_by_count":38,"area":null},{"id":"2207.07106","title":"Benchmarking Omni-Vision Representation through the Lens of Visual Realms","created":"2022-07-14","cited_by_count":38,"area":null},{"id":"2104.00679","title":"A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification","created":"2021-04-01","cited_by_count":36,"area":null},{"id":"2107.13782","title":"Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions","created":"2021-07-29","cited_by_count":35,"area":null},{"id":"2110.05922","title":"Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)","created":"2021-10-12","cited_by_count":35,"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":"2103.02093","title":"Pseudo-labeling for Scalable 3D Object Detection","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2104.00682","title":"Multiview Pseudo-Labeling for Semi-supervised Learning from Video","created":"2021-04-01","cited_by_count":32,"area":null},{"id":"2108.06332","title":"FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","created":"2021-08-13","cited_by_count":32,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2102.06073","title":"SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data","created":"2021-02-11","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":"2208.08789","title":"Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis","created":"2022-08-18","cited_by_count":29,"area":null},{"id":"2305.18035","title":"Physics-Informed Computer Vision: A Review and Perspectives","created":"2023-05-29","cited_by_count":28,"area":null},{"id":"2309.13190","title":"Spatial-frequency channels, shape bias, and adversarial robustness","created":"2023-09-22","cited_by_count":28,"area":null},{"id":"2106.11346","title":"GAIA: A Transfer Learning System of Object Detection that Fits Your Needs","created":"2021-06-21","cited_by_count":27,"area":null},{"id":"2203.04412","title":"ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","cited_by_count":27,"area":null},{"id":"2103.16554","title":"Pre-training strategies and datasets for facial representation learning","created":"2021-03-30","cited_by_count":26,"area":null},{"id":"2203.14448","title":"Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing","created":"2022-03-28","cited_by_count":26,"area":null},{"id":"2208.08631","title":"ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization","created":"2022-08-18","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":"2106.06080","title":"Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent","created":"2021-06-10","cited_by_count":21,"area":null},{"id":"2203.07845","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","created":"2022-03-15","cited_by_count":21,"area":null},{"id":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2203.16557","title":"COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical Image Segmentation based on Target-aware Domain Translation and Iterative Self-Training","created":"2022-03-30","cited_by_count":20,"area":null},{"id":"2204.07049","title":"Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking","created":"2022-04-14","cited_by_count":20,"area":null},{"id":"2404.01509","title":"Can Biases in ImageNet Models Explain Generalization?","created":"2024-04-01","cited_by_count":20,"area":null},{"id":"2406.00919","title":"Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2201.08514","title":"How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis","created":"2022-01-21","cited_by_count":19,"area":null},{"id":"2207.02335","title":"Multi-Label Retinal Disease Classification using Transformers","created":"2022-07-05","cited_by_count":19,"area":null},{"id":"2208.01489","title":"Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter","created":"2022-08-02","cited_by_count":18,"area":null},{"id":"2303.02344","title":"Improving Audio-Visual Video Parsing with Pseudo Visual Labels","created":"2023-03-04","cited_by_count":18,"area":null},{"id":"2306.03779","title":"Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex","created":"2023-06-06","cited_by_count":18,"area":null},{"id":"2404.17507","title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2112.08652","title":"Extreme Zero-Shot Learning for Extreme Text Classification","created":"2021-12-16","cited_by_count":15,"area":null},{"id":"2105.10420","title":"Self-learning for weakly supervised Gleason grading of local patterns","created":"2021-05-21","cited_by_count":14,"area":null},{"id":"2209.15383","title":"Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors","created":"2022-09-30","cited_by_count":14,"area":null},{"id":"2306.02595","title":"Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2312.03035","title":"SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2106.00609","title":"Robust Mutual Learning for Semi-supervised Semantic Segmentation","created":"2021-06-01","cited_by_count":13,"area":null},{"id":"2112.07194","title":"MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation","created":"2021-12-14","cited_by_count":13,"area":null},{"id":"2203.03871","title":"Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective","created":"2022-03-08","cited_by_count":13,"area":null},{"id":"2205.09904","title":"Deep transfer learning for image classification: a survey","created":"2022-05-20","cited_by_count":13,"area":null},{"id":"2210.06711","title":"Weighted Distillation with Unlabeled Examples","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2410.06020","title":"QT-DoG: Quantization-aware Training for Domain Generalization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2104.07767","title":"Exploring Visual Engagement Signals for Representation Learning","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2206.00809","title":"Distilling Knowledge from Object Classification to Aesthetics Assessment","created":"2022-06-02","cited_by_count":12,"area":null},{"id":"2210.09236","title":"ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2111.11595","title":"Semi-Supervised Learning with Taxonomic Labels","created":"2021-11-23","cited_by_count":11,"area":null},{"id":"2203.04049","title":"Graph Attention Transformer Network for Multi-Label Image Classification","created":"2022-03-08","cited_by_count":11,"area":null},{"id":"2203.09737","title":"Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation","created":"2022-03-18","cited_by_count":10,"area":null},{"id":"2211.10370","title":"Invariant Learning via Diffusion Dreamed Distribution Shifts","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2301.08390","title":"Open-Set Likelihood Maximization for Few-Shot Learning","created":"2023-01-20","cited_by_count":10,"area":null}],"next_cursor":"100"}