paper-with-me

홈 › Papers

Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness

2025-09-14 · Robin Narsingh Ranabhat, Longwei Wang, Amit Kumar Patel, KC santosh arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.11355

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningImage Classification

Similar Papers 제목 키워드 기반

The shape and simplicity biases of adversarially robust ImageNet-trained CNNs

2020-06-16 · Peijie Chen, Chirag Agarwal, Anh Nguyen

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 Generation

Frequency-domain Learning for Volumetric-based 3D Data Perception

2023-02-16 · Zifan Yu, Suya You, Fengbo Ren

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 Segmentation

On the Texture Bias for Few-Shot CNN Segmentation

2020-03-09 · Reza Azad, Abdur R Fayjie, Claude Kauffman, Ismail Ben Ayed 외

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 Segmentation

Assessing Shape Bias Property of Convolutional Neural Networks

2018-03-21 · Hossein Hosseini, Baicen Xiao, Mayoore Jaiswal, Radha Poovendran

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 Learning

Transformed Multi-view 3D Shape Features with Contrastive Learning

2025-10-22 · Márcus Vinícius Lobo Costa, Sherlon Almeida da Silva, Bárbara Caroline Benato, Leo Sampaio Ferraz Ribeiro 외 arxiv

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