{"total":102,"rows":[{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361,"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":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144,"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":"2312.03526","title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","created":"2023-12-06","cited_by_count":109,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"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":"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":"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":"2104.00887","title":"Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts","created":"2021-04-02","cited_by_count":46,"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":"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":"2206.03740","title":"Large Loss Matters in Weakly Supervised Multi-Label Classification","created":"2022-06-08","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":"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":"2304.05538","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":"2112.07368","title":"Simple and Robust Loss Design for Multi-Label Learning with Missing Labels","created":"2021-12-13","cited_by_count":30,"area":null},{"id":"2208.09913","title":"A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective","created":"2022-08-21","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":"2110.08890","title":"Network Augmentation for Tiny Deep Learning","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2202.05613","title":"CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning","created":"2022-02-11","cited_by_count":24,"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":"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":"2111.12172","title":"Multi-label Iterated Learning for Image Classification with Label Ambiguity","created":"2021-11-23","cited_by_count":19,"area":null},{"id":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","cited_by_count":19,"area":null},{"id":"2203.06127","title":"Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations","created":"2022-03-11","cited_by_count":17,"area":null},{"id":"2111.02331","title":"LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Training","created":"2021-11-03","cited_by_count":13,"area":null},{"id":"2206.01125","title":"Prefix Conditioning Unifies Language and Label Supervision","created":"2022-06-02","cited_by_count":13,"area":null},{"id":"2210.00094","title":"Improving Robustness with Adaptive Weight Decay","created":"2022-09-30","cited_by_count":13,"area":null},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2301.12549","title":"Unlocking Deterministic Robustness Certification on ImageNet","created":"2023-01-29","cited_by_count":13,"area":null},{"id":"2401.01764","title":"Understanding the Detrimental Class-level Effects of Data Augmentation","created":"2023-12-07","cited_by_count":13,"area":null},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2304.01804","title":"Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification","created":"2023-04-04","cited_by_count":11,"area":null},{"id":"2310.12152","title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","created":"2023-10-18","cited_by_count":11,"area":null},{"id":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2310.15985","title":"Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning","created":"2023-10-24","cited_by_count":10,"area":null},{"id":"2106.16209","title":"A data-centric approach for improving ambiguous labels with combined semi-supervised classification and clustering","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2204.03475","title":"Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2212.12977","title":"SMMix: Self-Motivated Image Mixing for Vision Transformers","created":"2022-12-26","cited_by_count":8,"area":null},{"id":"2301.00243","title":"Approaching Peak Ground Truth","created":"2022-12-31","cited_by_count":8,"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":"2403.06869","title":"Impact of Noisy Supervision in Foundation Model Learning","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2408.08172","title":"Towards flexible perception with visual memory","created":"2024-08-15","cited_by_count":8,"area":null},{"id":"2205.04227","title":"Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference","created":"2022-05-06","cited_by_count":7,"area":null},{"id":"2207.06224","title":"Beyond Hard Labels: Investigating data label distributions","created":"2022-07-13","cited_by_count":7,"area":null},{"id":"2112.14379","title":"Background-aware Classification Activation Map for Weakly Supervised Object Localization","created":"2021-12-29","cited_by_count":6,"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":"2307.14119","title":"A semantics-driven methodology for high-quality image annotation","created":"2023-07-26","cited_by_count":6,"area":null},{"id":"2106.01499","title":"Personalizing Pre-trained Models","created":"2021-06-02","cited_by_count":5,"area":null},{"id":"2110.04248","title":"Observations on K-image Expansion of Image-Mixing Augmentation for Classification","created":"2021-10-08","cited_by_count":5,"area":null},{"id":"2206.00501","title":"Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2206.10673","title":"Natural Backdoor Datasets","created":"2022-06-21","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":"2307.07680","title":"Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognition","created":"2023-07-15","cited_by_count":5,"area":null},{"id":"2308.12885","title":"Collect, Measure, Repeat: Reliability Factors for Responsible AI Data Collection","created":"2023-08-22","cited_by_count":5,"area":null},{"id":"2410.22952","title":"Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2203.00214","title":"Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data","created":"2022-03-01","cited_by_count":4,"area":null},{"id":"2210.11407","title":"Similarity of Neural Architectures using Adversarial Attack Transferability","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2212.06595","title":"OAMixer: Object-aware Mixing Layer for Vision Transformers","created":"2022-12-13","cited_by_count":4,"area":null},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2108.10549","title":"StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures","created":"2021-08-24","cited_by_count":3,"area":null},{"id":"2202.06054","title":"Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression","created":"2022-02-12","cited_by_count":3,"area":null},{"id":"2206.08653","title":"All Mistakes Are Not Equal: Comprehensive Hierarchy Aware Multi-label Predictions (CHAMP)","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2305.12811","title":"Label Smarter, Not Harder: CleverLabel for Faster Annotation of Ambiguous Image Classification with Higher Quality","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2401.03844","title":"Fully Attentional Networks with Self-emerging Token Labeling","created":"2024-01-08","cited_by_count":3,"area":null},{"id":"2506.04737","title":"Bridging Annotation Gaps: Transferring Labels to Align Object Detection Datasets","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2507.23509","title":"I Am Big, You Are Little; I Am Right, You Are Wrong","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2102.05884","title":"OpinionRank: Extracting Ground Truth Labels from Unreliable Expert Opinions with Graph-Based Spectral Ranking","created":"2021-02-11","cited_by_count":2,"area":null},{"id":"2108.00177","title":"Greedy Network Enlarging","created":"2021-07-31","cited_by_count":2,"area":null},{"id":"2110.08866","title":"Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2311.18540","title":"Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2403.08383","title":"AFGI: Towards Accurate and Fast-convergent Gradient Inversion Attack in Federated Learning","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2412.20924","title":"HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2504.02737","title":"RBT4DNN: Requirements-based Testing of Neural Networks","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2211.09061","title":"Squeeze flow of micro-droplets: convolutional neural network with trainable and tunable refinement","created":"2022-11-16","cited_by_count":1,"area":null},{"id":"2302.04391","title":"The Re-Label Method For Data-Centric Machine Learning","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2306.12189","title":"Annotating Ambiguous Images: General Annotation Strategy for High-Quality Data with Real-World Biomedical Validation","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2309.13886","title":"Can Class-Priors Help Single-Positive Multi-Label Learning?","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2403.08284","title":"MGIC: A Multi-Label Gradient Inversion Attack based on Canny Edge Detection on Federated Learning","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2412.18409","title":"The Impact of the Single-Label Assumption in Image Recognition Benchmarking","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2607.00916","title":"Condensing Large-Scale Datasets Directly with Minimal Information Loss","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.13783","title":"Doomed to Re-Annotate, Forever: The ImageNet Story","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2203.12350","title":"Hyper-Spectral Imaging for Overlapping Plastic Flakes Segmentation","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2205.14606","title":"A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks","created":"2022-05-29","cited_by_count":0,"area":null},{"id":"2305.18684","title":"ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2307.10577","title":"Ethosight: A Reasoning-Guided Iterative Learning System for Nuanced Perception based on Joint-Embedding & Contextual Label Affinity","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2407.15683","title":"Enhancing Transferability of Targeted Adversarial Examples: A Self-Universal Perspective","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2501.01844","title":"Learning from Ambiguous Data with Hard Labels","created":"2025-01-03","cited_by_count":0,"area":null},{"id":"2508.06556","title":"From Label Error Detection to Correction: A Modular Framework and Benchmark for Object Detection Datasets","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2601.17449","title":"DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2603.03808","title":"Vector-Quantized Soft Label Compression for Dataset Distillation","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.05729","title":"Unlocking ImageNet's Multi-Object Nature: Automated Large-Scale Multilabel Annotation","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.09613","title":"A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.14449","title":"Crowdsourcing of Real-world Image Annotation via Visual Properties","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2606.14555","title":"Rethinking Global Average Pooling: Your Classifier Is Secretly a Multi-Instance Learner","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":"100"}