shape bia

Decoupling Shape and Texture in SAM-2 via Controlled Texture Replacement WACV 2026 Contour Integration Underlies Human-Like Vision ICML 2025 Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization WACV 2025 Neuromanifold-Regularized KANs for Shape-fair Feature Representations ICCV 2025 Shape-Biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation WACV 2025 Can Biases in ImageNet Models Explain Generalization? CVPR 2024 Intriguing Properties of Generative Classifiers ICLR 2024 Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers CVPR 2024 Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation AAAI 2023 Edges to Shapes to Concepts: Adversarial Augmentation for Robust Vision CVPR 2023 Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity NeurIPS 2023 Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition ICCV 2023 Spatial-frequency channels, shape bias, and adversarial robustness NeurIPS 2023 On the Effects of Artificial Data Modification ICML 2022 Does enhanced shape bias improve neural network robustness to common corruptions? ICLR 2021 Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification CVPR 2021 Shape-Biased Domain Generalization via Shock Graph Embeddings ICCV 2021 Shape or Texture: Understanding Discriminative Features in CNNs ICLR 2021 The Emergence of the Shape Bias Results from Communicative Efficiency CoNLL 2021 Informative Dropout for Robust Representation Learning: A Shape-bias Perspective ICML 2020 The Origins and Prevalence of Texture Bias in Convolutional Neural Networks NeurIPS 2020 ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness ICLR 2019 Interpreting Adversarially Trained Convolutional Neural Networks ICML 2019 Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study ICML 2017