English

Texture Bias Of CNNs Limits Few-Shot Classification Performance

Machine Learning 2019-10-21 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1910.08519,
  title  = {Texture Bias Of CNNs Limits Few-Shot Classification Performance},
  author = {Sam Ringer and Will Williams and Tom Ash and Remi Francis and David MacLeod},
  journal= {arXiv preprint arXiv:1910.08519},
  year   = {2019}
}
R2 v1 2026-06-23T11:48:02.119Z