# Imbalanced Image Classification with Complement Cross Entropy

arXiv: https://arxiv.org/abs/2009.02189 · HTML: https://mlsanity.com/paper/2009.02189/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification](https://mlsanity.com/paper/2102.01284/) (2021)
- [Contrastive Attraction and Contrastive Repulsion for Representation Learning](https://mlsanity.com/paper/2105.03746/) (2021)
- [Dual Branch Deep Learning Network for Detection and Stage Grading of Diabetic Retinopathy](https://mlsanity.com/paper/2308.09945/) (2023)
- [Improving Tail-Class Representation with Centroid Contrastive Learning](https://mlsanity.com/paper/2110.10048/) (2021)
- [Dataset balancing can hurt model performance](https://mlsanity.com/paper/2307.00079/) (2023)
- [A generalised novel loss function for computational fluid dynamics](https://mlsanity.com/paper/2411.17059/) (2024)
- [Few-shot 1/a Anomalies Feedback : Damage Vision Mining Opportunity and Embedding Feature Imbalance](https://mlsanity.com/paper/2307.12676/) (2023)
- [Investigating Long-term Training for Remote Sensing Object Detection](https://mlsanity.com/paper/2407.15143/) (2024)
- [G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection](https://mlsanity.com/paper/2607.19942/) (2026)

## Abstract (arXiv)

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, in this paper, we concentrate on the study of cross entropy which mostly ignores output scores on incorrect classes. This work discovers that neutralizing predicted probabilities on incorrect classes improves the prediction accuracy for imbalanced image classification. This paper proposes a simple but effective loss named complement cross entropy based on this finding. The proposed 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 on imbalanced distributions. Extensive experiments on imbalanced datasets demonstrate the effectiveness of the proposed method.