Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness
Convolutional Neural Networks (CNNs) excel at image classification but remain vulnerable to common corruptions that humans handle with ease. A key reason for this fragility is their reliance on local texture cues rather than global object shapes -- a stark contrast to human perception. To address this, we propose two complementary regularization strategies designed to encourage shape-biased representations and enhance robustness. The first introduces an auxiliary loss that enforces feature consistency between original and low-frequency filtered inputs, discouraging dependence on high-frequency textures. The second incorporates supervised contrastive learning to structure the feature space around class-consistent, shape-relevant representations. Evaluated on the CIFAR-10-C benchmark, both methods improve corruption robustness without degrading clean accuracy. Our results suggest that loss-level regularization can effectively steer CNNs toward more shape-aware, resilient representations.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningImage ClassificationSimilar Papers 제목 키워드 기반
The shape and simplicity biases of adversarially robust ImageNet-trained CNNs
Increasingly more similarities between human vision and convolutional neural networks (CNNs) have been revealed in the past few years. Yet, vanilla CNNs often fall short in generalizing to adversarial or out-of-distribut…
Image GenerationFrequency-domain Learning for Volumetric-based 3D Data Perception
Frequency-domain learning draws attention due to its superior tradeoff between inference accuracy and input data size. Frequency-domain learning in 2D computer vision tasks has shown that 2D convolutional neural networks…
3D Shape ClassificationSemantic SegmentationOn the Texture Bias for Few-Shot CNN Segmentation
Despite the initial belief that Convolutional Neural Networks (CNNs) are driven by shapes to perform visual recognition tasks, recent evidence suggests that texture bias in CNNs provides higher performing models when lea…
Few-Shot LearningFew-Shot Semantic SegmentationSegmentationSemantic SegmentationAssessing Shape Bias Property of Convolutional Neural Networks
It is known that humans display "shape bias" when classifying new items, i.e., they prefer to categorize objects based on their shape rather than color. Convolutional Neural Networks (CNNs) are also designed to take into…
One-Shot LearningTransformed Multi-view 3D Shape Features with Contrastive Learning
This paper addresses the challenges in representation learning of 3D shape features by investigating state-of-the-art backbones paired with both contrastive supervised and self-supervised learning objectives. Computer vi…
Self-Supervised LearningRepresentation LearningContrastive Learning