Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers

01/19/2022
by   Max Wolff, et al.
0

Feature preference in Convolutional Neural Network (CNN) image classifiers is integral to their decision making process, and while the topic has been well studied, it is still not understood at a fundamental level. We test a range of task relevant feature attributes (including shape, texture, and color) with varying degrees of signal and noise in highly controlled CNN image classification experiments using synthetic datasets to determine feature preferences. We find that CNNs will prefer features with stronger signal strength and lower noise irrespective of whether the feature is texture, shape, or color. This provides guidance for a predictive model for task relevant feature preferences, demonstrates pathways for bias in machine models that can be avoided with careful controls on experimental setup, and suggests that comparisons between how humans and machines prefer task relevant features in vision classification tasks should be revisited. Code to reproduce experiments in this paper can be found at <https://github.com/mwolff31/signal_preference>.

READ FULL TEXT

page 2

page 3

page 9

research
07/15/2022

Image and Texture Independent Deep Learning Noise Estimation using Multiple Frames

In this study, a novel multiple-frame based image and texture independen...
research
03/09/2020

On the Texture Bias for Few-Shot CNN Segmentation

Despite the initial belief that Convolutional Neural Networks (CNNs) are...
research
07/19/2022

Contributions of Shape, Texture, and Color in Visual Recognition

We investigate the contributions of three important features of the huma...
research
07/13/2023

On the ability of CNNs to extract color invariant intensity based features for image classification

Convolutional neural networks (CNNs) have demonstrated remarkable succes...
research
01/27/2021

Shape or Texture: Understanding Discriminative Features in CNNs

Contrasting the previous evidence that neurons in the later layers of a ...
research
11/23/2022

BiasBed – Rigorous Texture Bias Evaluation

The well-documented presence of texture bias in modern convolutional neu...

Please sign up or login with your details

Forgot password? Click here to reset