# Texture Bias Of CNNs Limits Few-Shot Classification Performance

Source: [Texture Bias Of CNNs Limits Few-Shot Classification Performance](<https://www.sota2.com/research/paper/68fa668e1e209131cea10ccb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:52:21.192Z

Authors: Sam Ringer, Will Williams, Tom Ash, Remi Francis, David MacLeod

Published: 2019-10-18T17:30:11.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.08519>)

[PDF](<https://arxiv.org/pdf/1910.08519.pdf>)