Learning Visual Context by Comparison
This addresses the challenge of accurate medical image analysis for healthcare applications, but it is incremental as it builds on existing deep learning models.
The paper tackles the problem of disease detection in X-ray images by introducing an Attend-and-Compare Module (ACM) to model differences between regions, resulting in consistent improvements across chest X-ray recognition and COCO object detection tasks.
Finding diseases from an X-ray image is an important yet highly challenging task. Current methods for solving this task exploit various characteristics of the chest X-ray image, but one of the most important characteristics is still missing: the necessity of comparison between related regions in an image. In this paper, we present Attend-and-Compare Module (ACM) for capturing the difference between an object of interest and its corresponding context. We show that explicit difference modeling can be very helpful in tasks that require direct comparison between locations from afar. This module can be plugged into existing deep learning models. For evaluation, we apply our module to three chest X-ray recognition tasks and COCO object detection & segmentation tasks and observe consistent improvements across tasks. The code is available at https://github.com/mk-minchul/attend-and-compare.