Texture Bias Of CNNs Limits Few-Shot Classification Performance

10/18/2019
by   Sam Ringer, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset