Learning Visual Context by Comparison

TL;DR

This paper introduces the Attend-and-Compare Module (ACM), a novel component that explicitly models differences between related regions in images, improving performance in medical and object detection tasks.

Contribution

The paper proposes ACM, a plug-in module for deep learning models that enhances comparison between regions, addressing a key missing characteristic in current methods.

Findings

Consistent performance improvements across chest X-ray recognition tasks.

Enhanced object detection and segmentation results on COCO dataset.

Demonstrated versatility of ACM in different vision tasks.

Abstract

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.