The Change You Want to See

TL;DR

This paper presents a new scalable approach for object-level change detection in image pairs, leveraging co-attention architecture and diverse datasets to improve generalization across different domains and transformations.

Contribution

It introduces a novel co-attention based architecture and a large-scale dataset generation method for change detection, along with four diverse evaluation datasets.

Findings

Effective change detection across various datasets

Zero-shot generalization to unseen transformations

Superior performance over existing methods

Abstract

We live in a dynamic world where things change all the time. Given two images of the same scene, being able to automatically detect the changes in them has practical applications in a variety of domains. In this paper, we tackle the change detection problem with the goal of detecting "object-level" changes in an image pair despite differences in their viewpoint and illumination. To this end, we make the following four contributions: (i) we propose a scalable methodology for obtaining a large-scale change detection training dataset by leveraging existing object segmentation benchmarks; (ii) we introduce a co-attention based novel architecture that is able to implicitly determine correspondences between an image pair and find changes in the form of bounding box predictions; (iii) we contribute four evaluation datasets that cover a variety of domains and transformations, including synthetic image changes, real surveillance images of a 3D scene, and synthetic 3D scenes with camera motion; (iv) we evaluate our model on these four datasets and demonstrate zero-shot and beyond training transformation generalization.