Imbalanced Image Classification with Complement Cross Entropy

Abstract

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.

Adaptive Margin Aware Complement-Cross Entropy Loss for Improving Class Imbalance in Multi-View Sleep Staging Based on EEG Signals

“…In addition, Chen proposed complement entropy loss [32], which suppresses misclassification and achieves error neutralization by exploiting the complement information of samples in this class, thus improving the confidence level. Because the minority class is richer in error information, Kim et al [33] used complement entropy to improve the class imbalance problem. However, the existing complement entropy loss only considers the improvement of accuracy from the perspective of neutralizing the error information, and the available training samples are still insufficient for a very small percentage of minority class samples, which can limit the effectiveness of complement entropy loss for models in performing error neutralization of minority classes.…”

Contrastive Attraction and Contrastive Repulsion for Representation Learning

“…Here we create two class-imbalanced datasets with CIFAR-10 and CIFAR-100 to verify if CCT shows better robustness when this uniform prior assumption is violated. The imbalanced dataset is created by randomly sampling a certain number of samples from each class with a "linear" or "exponentional" rule (Kim et al, 2020). Specifically, given a dataset with C classes, for class l ∈ {1, 2, ..., C}, we randomly take samples with a proportion l C for "linear" rule and with a proportion exp( l C ) for "exponential" rule.…”