Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence

TL;DR

This paper introduces a novel zero-shot change detection method that incorporates visual correspondences to improve accuracy, reduce false positives, and enable change localization across different views and domains.

Contribution

It presents a new approach that uses change correspondences during training and testing, and predicts change regions with homography and Hungarian algorithm, advancing zero-shot change detection.

Findings

Achieves state-of-the-art change detection accuracy

Reduces false positive rates in zero-shot scenarios

Successfully predicts change correspondences with high precision

Abstract

Detecting object-level changes between two images across possibly different views is a core task in many applications that involve visual inspection or camera surveillance. Existing change-detection approaches suffer from three major limitations: (1) lack of evaluation on image pairs that contain no changes, leading to unreported false positive rates; (2) lack of correspondences (i.e., localizing the regions before and after a change); and (3) poor zero-shot generalization across different domains. To address these issues, we introduce a novel method that leverages change correspondences (a) during training to improve change detection accuracy, and (b) at test time, to minimize false positives. That is, we harness the supervision labels of where an object is added or removed to supervise change detectors, improving their accuracy over previous work by a large margin. Our work is also the first to predict correspondences between pairs of detected changes using estimated homography and the Hungarian algorithm. Our model demonstrates superior performance over existing methods, achieving state-of-the-art results in change detection and change correspondence accuracy across both in-distribution and zero-shot benchmarks.