Texture Bias Of CNNs Limits Few-Shot Classification Performance
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationFew-Shot LearningGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion
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+2On 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 SegmentationVessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images
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 SegmentationInformative Dropout for Robust Representation Learning: A Shape-bias Perspective
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 LearningThe Origins and Prevalence of Texture Bias in Convolutional Neural Networks
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