LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusion
This addresses the critical challenge of detecting rare medical conditions in histopathology, which is incremental as it builds on existing OOD detection and synthetic data methods.
The paper tackles the problem of detecting extremely rare classes in long-tailed histopathology data by treating them as out-of-distribution (OOD) data, using low-rank adaptation (LoRA) and diffusion guidance to generate synthetic data, resulting in improved OOD detection performance without compromising classification accuracy on head classes.
In realistic medical settings, the data are often inherently long-tailed, with most samples concentrated in a few classes and a long tail of rare classes, usually containing just a few samples. This distribution presents a significant challenge because rare conditions are critical to detect and difficult to classify due to limited data. In this paper, rather than attempting to classify rare classes, we aim to detect these as out-of-distribution data reliably. We leverage low-rank adaption (LoRA) and diffusion guidance to generate targeted synthetic data for the detection problem. We significantly improve the OOD detection performance on a challenging histopathological task with only ten samples per tail class without losing classification accuracy on the head classes.