{"total":72,"rows":[{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137,"area":null},{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97,"area":null},{"id":"2110.13771","title":"AugMax: Adversarial Composition of Random Augmentations for Robust Training","created":"2021-10-26","cited_by_count":90,"area":null},{"id":"2302.09462","title":"MedViT: A Robust Vision Transformer for Generalized Medical Image Classification","created":"2023-02-19","cited_by_count":89,"area":null},{"id":"2109.05211","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","created":"2021-09-11","cited_by_count":79,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2211.01201","title":"Human alignment of neural network representations","created":"2022-11-02","cited_by_count":74,"area":null},{"id":"2305.10665","title":"Content-based Unrestricted Adversarial Attack","created":"2023-05-18","cited_by_count":73,"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":"2207.03162","title":"Harnessing Out-Of-Distribution Examples via Augmenting Content and Style","created":"2022-07-07","cited_by_count":43,"area":null},{"id":"2103.13886","title":"Robust and Accurate Object Detection via Adversarial Learning","created":"2021-03-23","cited_by_count":42,"area":null},{"id":"2211.05568","title":"Unbiased Supervised Contrastive Learning","created":"2022-11-10","cited_by_count":40,"area":null},{"id":"2209.15605","title":"Bias Mimicking: A Simple Sampling Approach for Bias Mitigation","created":"2022-09-30","cited_by_count":30,"area":null},{"id":"2303.17096","title":"ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing","created":"2023-03-30","cited_by_count":30,"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":"2207.01156","title":"Removing Batch Normalization Boosts Adversarial Training","created":"2022-07-04","cited_by_count":24,"area":null},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23,"area":null},{"id":"2209.07735","title":"Enhance the Visual Representation via Discrete Adversarial Training","created":"2022-09-16","cited_by_count":23,"area":null},{"id":"2404.01509","title":"Can Biases in ImageNet Models Explain Generalization?","created":"2024-04-01","cited_by_count":20,"area":null},{"id":"2212.11237","title":"Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators","created":"2022-12-21","cited_by_count":17,"area":null},{"id":"2106.10938","title":"A Game-Theoretic Taxonomy of Visual Concepts in DNNs","created":"2021-06-21","cited_by_count":16,"area":null},{"id":"2207.09510","title":"Contributions of Shape, Texture, and Color in Visual Recognition","created":"2022-07-19","cited_by_count":16,"area":null},{"id":"2109.01087","title":"On-target Adaptation","created":"2021-09-02","cited_by_count":15,"area":null},{"id":"2504.04804","title":"DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery","created":"2025-04-07","cited_by_count":15,"area":null},{"id":"2106.13122","title":"Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers","created":"2021-06-24","cited_by_count":13,"area":null},{"id":"2201.11259","title":"Controlling Directions Orthogonal to a Classifier","created":"2022-01-27","cited_by_count":13,"area":null},{"id":"2509.20234","title":"ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2110.08220","title":"Combining Diverse Feature Priors","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2305.06568","title":"Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation","created":"2023-05-11","cited_by_count":12,"area":null},{"id":"2308.04553","title":"From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition","created":"2023-08-08","cited_by_count":12,"area":null},{"id":"2108.05779","title":"DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities","created":"2021-08-12","cited_by_count":10,"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":"2406.16422","title":"Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Prompting","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2109.05671","title":"Shape-Biased Domain Generalization via Shock Graph Embeddings","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2204.09838","title":"Fast AdvProp","created":"2022-04-21","cited_by_count":6,"area":null},{"id":"2208.04286","title":"Exploiting Shape Cues for Weakly Supervised Semantic Segmentation","created":"2022-08-08","cited_by_count":6,"area":null},{"id":"2210.15025","title":"Addressing Heterogeneity in Federated Learning via Distributional Transformation","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2206.05846","title":"InBiaseD: Inductive Bias Distillation to Improve Generalization and Robustness through Shape-awareness","created":"2022-06-12","cited_by_count":5,"area":null},{"id":"2401.08107","title":"Deep Shape-Texture Statistics for Completely Blind Image Quality Evaluation","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2212.04681","title":"Dynamic Test-Time Augmentation via Differentiable Functions","created":"2022-12-09","cited_by_count":4,"area":null},{"id":"2303.04896","title":"Using Positive Matching Contrastive Loss with Facial Action Units to mitigate bias in Facial Expression Recognition","created":"2023-03-08","cited_by_count":4,"area":null},{"id":"2311.06224","title":"Harnessing Synthetic Datasets: The Role of Shape Bias in Deep Neural Network Generalization","created":"2023-11-10","cited_by_count":4,"area":null},{"id":"2206.04831","title":"R4D: Utilizing Reference Objects for Long-Range Distance Estimation","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2211.11174","title":"Unveiling the Tapestry: the Interplay of Generalization and Forgetting in Continual Learning","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2403.11792","title":"SETA: Semantic-Aware Token Augmentation for Domain Generalization","created":"2024-03-18","cited_by_count":3,"area":null},{"id":"2410.14470","title":"How Do Training Methods Influence the Utilization of Vision Models?","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2503.12453","title":"Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2108.12001","title":"Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks","created":"2021-08-26","cited_by_count":2,"area":null},{"id":"2206.05323","title":"Memory Classifiers: Two-stage Classification for Robustness in Machine Learning","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2509.00765","title":"Decomposing and Revising What Language Models Generate","created":"2025-08-31","cited_by_count":2,"area":null},{"id":"2211.13190","title":"BiasBed -- Rigorous Texture Bias Evaluation","created":"2022-11-23","cited_by_count":1,"area":null},{"id":"2412.10597","title":"Err on the Side of Texture: Texture Bias on Real Data","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2507.10239","title":"Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2601.10836","title":"One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.13859","title":"Low-Pass Filtering Improves Behavioral Alignment of Vision Models","created":"2026-02-14","cited_by_count":1,"area":null},{"id":"2603.10834","title":"On the Reliability of Cue Conflict and Beyond","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.28450","title":"BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2103.14255","title":"Mixing-AdaSIN: Constructing a De-biased Dataset using Adaptive Structural Instance Normalization and Texture Mixing","created":"2021-03-26","cited_by_count":0,"area":null},{"id":"2106.04178","title":"White Paper Assistance: A Step Forward Beyond the Shortcut Learning","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2112.00954","title":"Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2203.12872","title":"Intrinsic Bias Identification on Medical Image Datasets","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2211.07277","title":"Robustifying Deep Vision Models Through Shape Sensitization","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2403.14140","title":"Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2405.18931","title":"EntProp: High Entropy Propagation for Improving Accuracy and Robustness","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2410.14878","title":"On the Influence of Shape, Texture and Color for Learning Semantic Segmentation","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2410.15416","title":"Contrast All the Time: Learning Time Series Representation from Temporal Consistency","created":"2024-10-20","cited_by_count":0,"area":null},{"id":"2412.09074","title":"DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain Generalization","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2502.11031","title":"A Critical Review of Predominant Bias in Neural Networks","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2503.16975","title":"EasyRobust: A Comprehensive and Easy-to-use Toolkit for Robust and Generalized Vision","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2510.05722","title":"Data Factory with Minimal Human Effort Using VLMs","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2601.05599","title":"Quantifying and Inducing Shape Bias in CNNs via Max-Pool Dilation","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2609.30478","title":"The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}