FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image Recognition

Abstract

Representational transfer from publicly available models is a promising technique for improving medical image classification, especially in long-tailed datasets with rare diseases. However, existing methods often overlook the frequency-dependent behavior of these models, thereby limiting their effectiveness in transferring representations and generalizations to rare diseases. In this paper, we propose FoPro-KD, a novel framework that leverages the power of frequency patterns learned from frozen pre-trained models to enhance their transferability and compression, presenting a few unique insights: 1) We demonstrate that leveraging representations from publicly available pre-trained models can substantially improve performance, specifically for rare classes, even when utilizing representations from a smaller pre-trained model. 2) We observe that pre-trained models exhibit frequency preferences, which we explore using our proposed Fourier Prompt Generator (FPG), allowing us to manipulate specific frequencies in the input image, enhancing the discriminative representational transfer. 3) By amplifying or diminishing these frequencies in the input image, we enable Effective Knowledge Distillation (EKD). EKD facilitates the transfer of knowledge from pre-trained models to smaller models. Through extensive experiments in long-tailed gastrointestinal image recognition and skin lesion classification, where rare diseases are prevalent, our FoPro-KD framework outperforms existing methods, enabling more accessible medical models for rare disease classification. Code is available at https://github.com/xmed-lab/FoPro-KD.

Accepted at IEEE TMI, code is available at https://github.com/xmed-lab/FoPro-KD

References in corpus (10)

• Conditional Generative Adversarial Nets
• Bootstrap your own latent: A new approach to self-supervised Learning
• FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
• Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study
• Contrastive Model Inversion for Data-Free Knowledge Distillation
• LPT: Long-tailed Prompt Tuning for Image Classification
• ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image Segmentation
• On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning
• Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach
• Differences between human and machine perception in medical diagnosis