Mix-up Self-Supervised Learning for Contrast-agnostic Applications
This addresses a specific bottleneck for medical image classification and similar domains where contrastive methods fail due to low image variance, offering an incremental improvement.
The paper tackles the problem of contrastive self-supervised learning degrading in contrast-agnostic applications like medical image classification, where images are visually similar, by proposing a mix-up self-supervised learning framework that improves top-1 accuracy by 2.5% to 7.4% compared to existing methods.
Contrastive self-supervised learning has attracted significant research attention recently. It learns effective visual representations from unlabeled data by embedding augmented views of the same image close to each other while pushing away embeddings of different images. Despite its great success on ImageNet classification, COCO object detection, etc., its performance degrades on contrast-agnostic applications, e.g., medical image classification, where all images are visually similar to each other. This creates difficulties in optimizing the embedding space as the distance between images is rather small. To solve this issue, we present the first mix-up self-supervised learning framework for contrast-agnostic applications. We address the low variance across images based on cross-domain mix-up and build the pretext task based on two synergistic objectives: image reconstruction and transparency prediction. Experimental results on two benchmark datasets validate the effectiveness of our method, where an improvement of 2.5% ~ 7.4% in top-1 accuracy was obtained compared to existing self-supervised learning methods.