{"total":237,"rows":[{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528,"area":null},{"id":"2209.07522","title":"Test-Time Training with Masked Autoencoders","created":"2022-09-15","cited_by_count":212,"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":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2303.11040","title":"Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving","created":"2023-03-20","cited_by_count":114,"area":null},{"id":"2102.11273","title":"On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness","created":"2021-02-22","cited_by_count":97,"area":null},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","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":"2103.02325","title":"On the effectiveness of adversarial training against common corruptions","created":"2021-03-03","cited_by_count":71,"area":null},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65,"area":null},{"id":"2105.06422","title":"Causally motivated Shortcut Removal Using Auxiliary Labels","created":"2021-05-13","cited_by_count":55,"area":null},{"id":"2107.05446","title":"Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration","created":"2021-07-12","cited_by_count":50,"area":null},{"id":"2209.09554","title":"Towards Robust Referring Image Segmentation","created":"2022-09-20","cited_by_count":49,"area":null},{"id":"2112.00639","title":"A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?","created":"2021-12-01","cited_by_count":48,"area":null},{"id":"2210.03895","title":"ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints","created":"2022-10-08","cited_by_count":48,"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":"2105.06152","title":"When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks","created":"2021-05-13","cited_by_count":41,"area":null},{"id":"2303.05470","title":"Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases","created":"2023-03-09","cited_by_count":41,"area":null},{"id":"2112.13547","title":"PRIME: A few primitives can boost robustness to common corruptions","created":"2021-12-27","cited_by_count":40,"area":null},{"id":"2306.04507","title":"Improving neural network representations using human similarity judgments","created":"2023-06-07","cited_by_count":38,"area":null},{"id":"2202.00728","title":"Physical Design using Differentiable Learned Simulators","created":"2022-02-01","cited_by_count":37,"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":"2104.12928","title":"If your data distribution shifts, use self-learning","created":"2021-04-27","cited_by_count":36,"area":null},{"id":"2204.05289","title":"Towards Online Domain Adaptive Object Detection","created":"2022-04-11","cited_by_count":36,"area":null},{"id":"2103.16241","title":"Improving robustness against common corruptions with frequency biased models","created":"2021-03-30","cited_by_count":34,"area":null},{"id":"2110.06513","title":"Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions","created":"2021-10-13","cited_by_count":34,"area":null},{"id":"2104.09789","title":"Does enhanced shape bias improve neural network robustness to common corruptions?","created":"2021-04-20","cited_by_count":32,"area":null},{"id":"2306.02080","title":"Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models","created":"2023-06-03","cited_by_count":31,"area":"mllm"},{"id":"2312.10165","title":"Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization","created":"2023-12-15","cited_by_count":31,"area":null},{"id":"2209.11459","title":"TeST: Test-time Self-Training under Distribution Shift","created":"2022-09-23","cited_by_count":29,"area":null},{"id":"2104.01086","title":"Defending Against Image Corruptions Through Adversarial Augmentations","created":"2021-04-02","cited_by_count":28,"area":null},{"id":"2107.14344","title":"Towards robust vision by multi-task learning on monkey visual cortex","created":"2021-07-29","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":"2405.05012","title":"The Entropy Enigma: Success and Failure of Entropy Minimization","created":"2024-05-08","cited_by_count":24,"area":null},{"id":"2108.03004","title":"MmWave Radar and Vision Fusion for Object Detection in Autonomous Driving: A Review","created":"2021-08-06","cited_by_count":23,"area":null},{"id":"2302.10164","title":"Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts","created":"2023-02-20","cited_by_count":23,"area":null},{"id":"2406.19087","title":"Dimensions underlying the representational alignment of deep neural networks with humans","created":"2024-06-27","cited_by_count":22,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2305.06024","title":"A Survey on the Robustness of Computer Vision Models against Common Corruptions","created":"2023-05-10","cited_by_count":21,"area":null},{"id":"2110.05861","title":"Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2101.07337","title":"Dissonance Between Human and Machine Understanding","created":"2021-01-18","cited_by_count":18,"area":null},{"id":"2207.03586","title":"CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationships","created":"2022-07-07","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":"2206.07736","title":"Improving Diversity with Adversarially Learned Transformations for Domain Generalization","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2206.10816","title":"Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming","created":"2022-06-22","cited_by_count":15,"area":null},{"id":"2302.14309","title":"Temporal Coherent Test-Time Optimization for Robust Video Classification","created":"2023-02-28","cited_by_count":15,"area":null},{"id":"2309.12821","title":"A Spectral Theory of Neural Prediction and Alignment","created":"2023-09-22","cited_by_count":14,"area":null},{"id":"2310.04780","title":"IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers","created":"2023-10-07","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":"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":"2307.13136","title":"Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?","created":"2023-07-24","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":"2510.23191","title":"The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models","created":"2025-10-27","cited_by_count":13,"area":null},{"id":"2108.00107","title":"Comparing object recognition in humans and deep convolutional neural networks -- An eye tracking study","created":"2021-07-30","cited_by_count":12,"area":null},{"id":"2203.07302","title":"Mixed Evidence for Gestalt Grouping in Deep Neural Networks","created":"2022-03-14","cited_by_count":12,"area":null},{"id":"2103.12329","title":"Contrastive Reasoning in Neural Networks","created":"2021-03-23","cited_by_count":11,"area":null},{"id":"2110.00899","title":"Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function","created":"2021-10-03","cited_by_count":11,"area":null},{"id":"2110.04545","title":"Towards Data-Free Domain Generalization","created":"2021-10-09","cited_by_count":11,"area":null},{"id":"2202.03930","title":"If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components","created":"2022-02-08","cited_by_count":11,"area":null},{"id":"2206.11939","title":"Measuring Representational Robustness of Neural Networks Through Shared Invariances","created":"2022-06-23","cited_by_count":11,"area":null},{"id":"2207.00887","title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","created":"2022-07-02","cited_by_count":11,"area":null},{"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":"2605.29330","title":"EarthShift: a benchmark for measuring robustness to real-world distribution shifts in Earth observation","created":"2026-05-28","cited_by_count":11,"area":null},{"id":"2110.01476","title":"Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training","created":"2021-10-04","cited_by_count":10,"area":null},{"id":"2202.08340","title":"A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines","created":"2022-02-16","cited_by_count":10,"area":null},{"id":"2206.02664","title":"Learning with Capsules: A Survey","created":"2022-06-06","cited_by_count":10,"area":null},{"id":"2209.09423","title":"Fairness and robustness in anti-causal prediction","created":"2022-09-20","cited_by_count":10,"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":"2401.09109","title":"Trapped in texture bias? A large scale comparison of deep instance segmentation","created":"2024-01-17","cited_by_count":10,"area":null},{"id":"2504.16940","title":"Better artificial intelligence does not mean better models of biology","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2102.11731","title":"Rethinking Natural Adversarial Examples for Classification Models","created":"2021-02-23","cited_by_count":9,"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":"2211.11925","title":"Multimodal Data Augmentation for Visual-Infrared Person ReID with Corrupted Data","created":"2022-11-22","cited_by_count":9,"area":null},{"id":"2303.12669","title":"An Extended Study of Human-like Behavior under Adversarial Training","created":"2023-03-22","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":"2109.01123","title":"Benchmarking the Robustness of Instance Segmentation Models","created":"2021-09-02","cited_by_count":8,"area":null},{"id":"2301.12993","title":"Benchmarking Robustness to Adversarial Image Obfuscations","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2405.09582","title":"AD-Aligning: Emulating Human-like Generalization for Cognitive Domain Adaptation in Deep Learning","created":"2024-05-15","cited_by_count":8,"area":null},{"id":"2407.11906","title":"SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2102.06406","title":"A Too-Good-to-be-True Prior to Reduce Shortcut Reliance","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2112.12175","title":"Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2202.12412","title":"Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration","created":"2022-02-24","cited_by_count":7,"area":null},{"id":"2209.03519","title":"Measuring Human Perception to Improve Open Set Recognition","created":"2022-09-08","cited_by_count":7,"area":null},{"id":"2211.06797","title":"Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling","created":"2022-11-13","cited_by_count":7,"area":null},{"id":"2302.02944","title":"Learning Complementary Policies for Human-AI Teams","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2308.11677","title":"An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning","created":"2023-08-22","cited_by_count":7,"area":null},{"id":"2308.15378","title":"On the Robustness of Object Detection Models on Aerial Images","created":"2023-08-29","cited_by_count":7,"area":null},{"id":"2406.16540","title":"Improving robustness to corruptions with multiplicative weight perturbations","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2103.05137","title":"Contemplating real-world object classification","created":"2021-03-08","cited_by_count":6,"area":null},{"id":"2408.16265","title":"Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classification","created":"2024-08-29","cited_by_count":6,"area":null},{"id":"2110.10645","title":"Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs","created":"2021-10-20","cited_by_count":5,"area":null},{"id":"2201.12123","title":"DELAUNAY: a dataset of abstract art for psychophysical and machine learning research","created":"2022-01-28","cited_by_count":5,"area":null},{"id":"2201.12440","title":"Certifying Model Accuracy under Distribution Shifts","created":"2022-01-28","cited_by_count":5,"area":null},{"id":"2208.06987","title":"The Causal Structure of Domain Invariant Supervised Representation Learning","created":"2022-08-15","cited_by_count":5,"area":null},{"id":"2210.15999","title":"Benchmarking performance of object detection under image distortions in an uncontrolled environment","created":"2022-10-28","cited_by_count":5,"area":null},{"id":"2302.14302","title":"Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain","created":"2023-02-28","cited_by_count":5,"area":null},{"id":"2308.00854","title":"Training on Foveated Images Improves Robustness to Adversarial Attacks","created":"2023-08-01","cited_by_count":5,"area":null},{"id":"2405.16493","title":"Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception","created":"2024-05-26","cited_by_count":5,"area":null}],"next_cursor":"100"}