Anisotropic Diffusion Probabilistic Model for Imbalanced Image Classification

TL;DR

This paper introduces the Anisotropic Diffusion Probabilistic Model (ADPM), which enhances imbalanced image classification by controlling diffusion speeds based on data distribution, improving rare class accuracy in medical datasets.

Contribution

The paper proposes a novel anisotropic diffusion approach that adjusts diffusion based on class imbalance and integrates spatial and semantic priors for better classification of tail classes.

Findings

Significant improvement in F1-scores for rare classes on medical datasets.

Effective handling of long-tail data with improved tail class accuracy.

Maintains high accuracy on head classes while boosting tail class performance.

Abstract

Real-world data often has a long-tailed distribution, where the scarcity of tail samples significantly limits the model's generalization ability. Denoising Diffusion Probabilistic Models (DDPM) are generative models based on stochastic differential equation theory and have demonstrated impressive performance in image classification tasks. However, existing diffusion probabilistic models do not perform satisfactorily in classifying tail classes. In this work, we propose the Anisotropic Diffusion Probabilistic Model (ADPM) for imbalanced image classification problems. We utilize the data distribution to control the diffusion speed of different class samples during the forward process, effectively improving the classification accuracy of the denoiser in the reverse process. Specifically, we provide a theoretical strategy for selecting noise levels for different categories in the diffusion process based on error analysis theory to address the imbalanced classification problem. Furthermore, we integrate global and local image prior in the forward process to enhance the model's discriminative ability in the spatial dimension, while incorporate semantic-level contextual information in the reverse process to boost the model's discriminative power and robustness. Through comparisons with state-of-the-art methods on four medical benchmark datasets, we validate the effectiveness of the proposed method in handling long-tail data. Our results confirm that the anisotropic diffusion model significantly improves the classification accuracy of rare classes while maintaining the accuracy of head classes. On the skin lesion datasets, PAD-UFES and HAM10000, the F1-scores of our method improved by 4% and 3%, respectively compared to the original diffusion probabilistic model.