Imbalanced Image Classification with Complement Cross Entropy

09/04/2020
by   Yechan Kim, et al.
87

Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets. However, imbalanced class distributions still limit the wide applicability of these models due to degradation in performance. To solve this problem, we focus on the study of cross entropy: it mostly ignores output scores on wrong classes. In this work, we discover that neutralizing predicted probabilities on incorrect classes helps improve accuracy of prediction for imbalanced image classification. This paper proposes a simple but effective loss named complement cross entropy (CCE) based on this finding. Our loss makes the ground truth class overwhelm the other classes in terms of softmax probability, by neutralizing probabilities of incorrect classes, without additional training procedures. Along with it, this loss facilitates the models to learn key information especially from samples on minority classes. It ensures more accurate and robust classification results for imbalanced class distributions. Extensive experiments on imbalanced datasets demonstrate the effectiveness of our method compared to other state-of-the-art methods.

READ FULL TEXT

page 3

page 4

research
03/04/2019

Complement Objective Training

Learning with a primary objective, such as softmax cross entropy for cla...
research
12/19/2019

Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks

Deep neural networks have improved image classification dramatically ove...
research
08/21/2023

A step towards understanding why classification helps regression

A number of computer vision deep regression approaches report improved r...
research
07/03/2020

Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data

Deep convolution neural network has attracted many attentions in large-s...
research
03/23/2019

Improving Adversarial Robustness via Guided Complement Entropy

Model robustness has been an important issue, since adding small adversa...
research
10/03/2022

Language-Aware Soft Prompting for Vision Language Foundation Models

This paper is on soft prompt learning for Vision & Language (V L) mode...
research
11/17/2016

Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks

In the context of single-label classification, despite the huge success ...

Please sign up or login with your details

Forgot password? Click here to reset