# Learning Visual Context by Comparison

arXiv: https://arxiv.org/abs/2007.07506 · HTML: https://mlsanity.com/paper/2007.07506/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-Contrast CT Scans](https://mlsanity.com/paper/2206.15445/) (2022)
- [Fine-Grained Attention for Weakly Supervised Object Localization](https://mlsanity.com/paper/2104.04952/) (2021)
- [Look at here : Utilizing supervision to attend subtle key regions](https://mlsanity.com/paper/2111.13233/) (2021)
- [Deep Learning-Based Breast Cancer Detection in Mammography: A Multi-Center Validation Study in Thai Population](https://mlsanity.com/paper/2506.03177/) (2025)
- [From Classification to Localization and Clinical Validation: Large-Scale Development of a Deep Learning System for Thoracic Disease Detection on Chest Radiographs in Thailand](https://mlsanity.com/paper/2607.09305/) (2026)

## Abstract (arXiv)

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.