paper-with-me

홈 › Papers

Texture Bias Of CNNs Limits Few-Shot Classification Performance

2019-10-18 · Sam Ringer, Will Williams, Tom Ash, Remi Francis, David MacLeod

Accurate image classification given small amounts of labelled data (few-shot classification) remains an open problem in computer vision. In this work we examine how the known texture bias of Convolutional Neural Networks (CNNs) affects few-shot classification performance. Although texture bias can help in standard image classification, in this work we show it significantly harms few-shot classification performance. After correcting this bias we demonstrate state-of-the-art performance on the competitive miniImageNet task using a method far simpler than the current best performing few-shot learning approaches.

📄 PDF Abstract BibTeX arXiv:1910.08519

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationFew-Shot LearningGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion

2024-02-14 · Edgar Heinert, Matthias Rottmann, Kira Maag, Karsten Kahl

Convolutional neural networks (CNNs) for image processing tend to focus on localized texture patterns, commonly referred to as texture bias. While most of the previous works in the literature focus on the task of image c…

Adversarial RobustnessDomain Generalizationimage-classificationImage Classification+2

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

VessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images

2025-10-31 · Cesar H. Comin, Wesley N. Galvão arxiv

Semantic segmentation of blood vessels is an important task in medical image analysis, but its progress is often hindered by the scarcity of large annotated datasets and the poor generalization of models across different…

Semantic Segmentation

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

2020-08-10 · ICML 2020 1 · Baifeng Shi, Dinghuai Zhang, Qi Dai, Zhanxing Zhu 외

Convolutional Neural Networks (CNNs) are known to rely more on local texture rather than global shape when making decisions. Recent work also indicates a close relationship between CNN's texture-bias and its robustness a…

Domain GeneralizationRepresentation Learning

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks

2019-11-20 · NeurIPS 2020 12 · Katherine L. Hermann, Ting Chen, Simon Kornblith

Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. How pervasive is this bias, and where does it come from? We find that, when trained on dataset…

Data AugmentationObject Recognition