{"total":295,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109,"area":null},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446,"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":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999,"area":null},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947,"area":null},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691,"area":null},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577,"area":null},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475,"area":null},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"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":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267,"area":null},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260,"area":null},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260,"area":null},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248,"area":null},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234,"area":null},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172,"area":null},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172,"area":null},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165,"area":null},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2109.04270","title":"Toward a Perspectivist Turn in Ground Truthing for Predictive Computing","created":"2021-09-09","cited_by_count":130,"area":null},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127,"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":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117,"area":null},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103,"area":null},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102,"area":null},{"id":"2112.01716","title":"Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research","created":"2021-12-03","cited_by_count":102,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"area":null},{"id":"2106.03149","title":"Large-scale Unsupervised Semantic Segmentation","created":"2021-06-06","cited_by_count":101,"area":null},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88,"area":null},{"id":"2302.14301","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking","created":"2023-02-28","cited_by_count":85,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80,"area":null},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80,"area":null},{"id":"2402.19460","title":"Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks","created":"2024-02-29","cited_by_count":78,"area":null},{"id":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76,"area":null},{"id":"2105.04522","title":"Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels","created":"2021-05-10","cited_by_count":74,"area":null},{"id":"2211.01201","title":"Human alignment of neural network representations","created":"2022-11-02","cited_by_count":74,"area":null},{"id":"2210.01033","title":"LPT: Long-tailed Prompt Tuning for Image Classification","created":"2022-10-03","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":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2403.13043","title":"When Do We Not Need Larger Vision Models?","created":"2024-03-19","cited_by_count":67,"area":null},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65,"area":null},{"id":"2306.05175","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","created":"2023-06-08","cited_by_count":63,"area":null},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62,"area":null},{"id":"2205.04596","title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","created":"2022-05-09","cited_by_count":61,"area":null},{"id":"2212.00653","title":"Hyperbolic Contrastive Learning for Visual Representations beyond Objects","created":"2022-12-01","cited_by_count":61,"area":null},{"id":"2209.14981","title":"Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging","created":"2022-09-29","cited_by_count":54,"area":null},{"id":"2105.14217","title":"Less is More: Pay Less Attention in Vision Transformers","created":"2021-05-29","cited_by_count":53,"area":null},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51,"area":null},{"id":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50,"area":null},{"id":"2106.02990","title":"Self-Damaging Contrastive Learning","created":"2021-06-06","cited_by_count":48,"area":null},{"id":"2207.08409","title":"TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers","created":"2022-07-18","cited_by_count":48,"area":null},{"id":"2203.16481","title":"On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification","created":"2022-03-30","cited_by_count":46,"area":null},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","cited_by_count":46,"area":null},{"id":"2212.01758","title":"Improving Zero-shot Generalization and Robustness of Multi-modal Models","created":"2022-12-04","cited_by_count":45,"area":null},{"id":"2109.00574","title":"Active label cleaning for improved dataset quality under resource constraints","created":"2021-09-01","cited_by_count":44,"area":null},{"id":"2211.01866","title":"ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations","created":"2022-11-03","cited_by_count":44,"area":null},{"id":"2110.14189","title":"Robust Contrastive Learning Using Negative Samples with Diminished Semantics","created":"2021-10-27","cited_by_count":43,"area":null},{"id":"2204.08446","title":"VSA: Learning Varied-Size Window Attention in Vision Transformers","created":"2022-04-18","cited_by_count":43,"area":null},{"id":"2207.00810","title":"Eliciting and Learning with Soft Labels from Every Annotator","created":"2022-07-02","cited_by_count":43,"area":null},{"id":"2207.06214","title":"Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimation","created":"2022-07-13","cited_by_count":43,"area":null},{"id":"2403.01931","title":"VariErr NLI: Separating Annotation Error from Human Label Variation","created":"2024-03-04","cited_by_count":42,"area":null},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41,"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":"2111.15121","title":"Pyramid Adversarial Training Improves ViT Performance","created":"2021-11-30","cited_by_count":39,"area":null},{"id":"2208.00780","title":"Visual correspondence-based explanations improve AI robustness and human-AI team accuracy","created":"2022-07-26","cited_by_count":39,"area":null},{"id":"2303.11324","title":"Open-vocabulary Panoptic Segmentation with Embedding Modulation","created":"2023-03-20","cited_by_count":39,"area":null},{"id":"2106.03714","title":"Refiner: Refining Self-attention for Vision Transformers","created":"2021-06-07","cited_by_count":38,"area":null},{"id":"2103.10292","title":"How I failed machine learning in medical imaging -- shortcomings and recommendations","created":"2021-03-18","cited_by_count":37,"area":null},{"id":"2105.10305","title":"Correlated Input-Dependent Label Noise in Large-Scale Image Classification","created":"2021-05-19","cited_by_count":37,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"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":"2111.10493","title":"Discrete Representations Strengthen Vision Transformer Robustness","created":"2021-11-20","cited_by_count":35,"area":null},{"id":"2301.04644","title":"Does progress on ImageNet transfer to real-world datasets?","created":"2023-01-11","cited_by_count":35,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2304.09856","title":"LipsFormer: Introducing Lipschitz Continuity to Vision Transformers","created":"2023-04-19","cited_by_count":34,"area":null},{"id":"2304.05538","title":"ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification","created":"2023-04-11","cited_by_count":33,"area":null},{"id":"2107.09234","title":"Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior","created":"2021-07-20","cited_by_count":29,"area":null},{"id":"2106.12447","title":"How Well do Feature Visualizations Support Causal Understanding of CNN Activations?","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2111.12880","title":"Active Learning at the ImageNet Scale","created":"2021-11-25","cited_by_count":28,"area":null},{"id":"2103.10107","title":"Danish Fungi 2020 -- Not Just Another Image Recognition Dataset","created":"2021-03-18","cited_by_count":27,"area":null},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","cited_by_count":27,"area":null},{"id":"2202.00395","title":"Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2210.16870","title":"A simple, efficient and scalable contrastive masked autoencoder for learning visual representations","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2203.16219","title":"Acknowledging the Unknown for Multi-label Learning with Single Positive Labels","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2208.11695","title":"Bugs in the Data: How ImageNet Misrepresents Biodiversity","created":"2022-08-24","cited_by_count":24,"area":null}],"next_cursor":"100"}