Visual In-Context Learning for Few-Shot Eczema Segmentation

TL;DR

This paper demonstrates that visual in-context learning with SegGPT enables effective few-shot eczema segmentation, outperforming traditional CNN models trained on large datasets, and highlights its potential for inclusive skin imaging solutions.

Contribution

The study introduces a novel application of SegGPT for few-shot eczema segmentation, showing superior performance with minimal examples without retraining.

Findings

SegGPT with 2 examples outperforms U-Net trained on 428 images.

Using more examples can decrease SegGPT's performance.

Visual in-context learning accelerates skin imaging tasks.

Abstract

Automated diagnosis of eczema from digital camera images is crucial for developing applications that allow patients to self-monitor their recovery. An important component of this is the segmentation of eczema region from such images. Current methods for eczema segmentation rely on deep neural networks such as convolutional (CNN)-based U-Net or transformer-based Swin U-Net. While effective, these methods require high volume of annotated data, which can be difficult to obtain. Here, we investigate the capabilities of visual in-context learning that can perform few-shot eczema segmentation with just a handful of examples and without any need for retraining models. Specifically, we propose a strategy for applying in-context learning for eczema segmentation with a generalist vision model called SegGPT. When benchmarked on a dataset of annotated eczema images, we show that SegGPT with just 2 representative example images from the training dataset performs better (mIoU: 36.69) than a CNN U-Net trained on 428 images (mIoU: 32.60). We also discover that using more number of examples for SegGPT may in fact be harmful to its performance. Our result highlights the importance of visual in-context learning in developing faster and better solutions to skin imaging tasks. Our result also paves the way for developing inclusive solutions that can cater to minorities in the demographics who are typically heavily under-represented in the training data.