{"total":51,"rows":[{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446,"area":null},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2210.07506","title":"Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation","created":"2022-10-14","cited_by_count":86,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"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":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27,"area":null},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2206.02846","title":"A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information","created":"2022-06-06","cited_by_count":26,"area":null},{"id":"2309.01439","title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","created":"2023-09-04","cited_by_count":25,"area":null},{"id":"2205.11083","title":"Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation","created":"2022-05-23","cited_by_count":24,"area":null},{"id":"2303.11546","title":"Texture Learning Domain Randomization for Domain Generalized Segmentation","created":"2023-03-21","cited_by_count":24,"area":null},{"id":"2310.07473","title":"FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation","created":"2023-10-11","cited_by_count":22,"area":null},{"id":"2404.01509","title":"Can Biases in ImageNet Models Explain Generalization?","created":"2024-04-01","cited_by_count":20,"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":"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":"2108.07884","title":"Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs","created":"2021-08-17","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":"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":"2108.09929","title":"SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness","created":"2021-08-23","cited_by_count":7,"area":null},{"id":"2211.01783","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","created":"2022-11-03","cited_by_count":7,"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":"2210.02748","title":"CLAD: A Contrastive Learning based Approach for Background Debiasing","created":"2022-10-06","cited_by_count":6,"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":"2107.06532","title":"Graph Jigsaw Learning for Cartoon Face Recognition","created":"2021-07-14","cited_by_count":4,"area":null},{"id":"2301.03169","title":"A Study on the Generality of Neural Network Structures for Monocular Depth Estimation","created":"2023-01-09","cited_by_count":4,"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":"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":"2110.10332","title":"AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging: Towards Radiophenomics","created":"2021-10-20","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":"2311.11029","title":"Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen Classification from Microscopic Images","created":"2023-11-18","cited_by_count":2,"area":null},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","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":"2604.01341","title":"Perceptual misalignment of texture representations in convolutional neural networks","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2110.10335","title":"Simpler Does It: Generating Semantic Labels with Objectness Guidance","created":"2021-10-20","cited_by_count":1,"area":null},{"id":"2301.10608","title":"Connecting metrics for shape-texture knowledge in computer vision","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2510.26560","title":"On Measuring Localization of Shortcuts in Deep Networks","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2211.07277","title":"Robustifying Deep Vision Models Through Shape Sensitization","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2212.01470","title":"Prediction of Scene Plausibility","created":"2022-12-02","cited_by_count":0,"area":null},{"id":"2307.06500","title":"On the ability of CNNs to extract color invariant intensity based features for image classification","created":"2023-07-13","cited_by_count":0,"area":null},{"id":"2405.13860","title":"MAGIC: Map-Guided Few-Shot Audio-Visual Acoustics Modeling","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2408.17083","title":"Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning","created":"2024-08-30","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":"2503.02302","title":"On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2510.27646","title":"VessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2604.25065","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2607.05641","title":"VEIL: How Visual Encoding Hijacking Induces Bias In Vision Models","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.16298","title":"Revisiting Shape and Texture Reliance with Category-Separability-Calibrated Suppression","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.23371","title":"Investigating the Visual Cues of CNNs for Vascular Segmentation: A Case Study in Microscopy and Fundus Imaging","created":"2026-07-25","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}