# The Change You Want to See

arXiv: https://arxiv.org/abs/2209.14341 · HTML: https://mlsanity.com/paper/2209.14341/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [Tracking Emerges by Colorizing Videos](https://mlsanity.com/paper/1806.09594/) (2018)
- [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://mlsanity.com/paper/1803.02579/) (2018)
- [Learning to Describe Differences Between Pairs of Similar Images](https://mlsanity.com/paper/1808.10584/) (2018)
- [MAST: A Memory-Augmented Self-supervised Tracker](https://mlsanity.com/paper/2002.07793/) (2020)
- [Learning Feature Descriptors using Camera Pose Supervision](https://mlsanity.com/paper/2004.13324/) (2020)
- [Weakly Supervised Silhouette-based Semantic Scene Change Detection](https://mlsanity.com/paper/1811.11985/) (2018)
- [Hierarchical Paired Channel Fusion Network for Street Scene Change Detection](https://mlsanity.com/paper/2010.09925/) (2020)
- [ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments](https://mlsanity.com/paper/2103.05368/) (2021)
- [Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences](https://mlsanity.com/paper/1803.07231/) (2018)
- [Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting](https://mlsanity.com/paper/2106.01532/) (2021)
- [Epipolar-Guided Deep Object Matching for Scene Change Detection](https://mlsanity.com/paper/2007.15540/) (2020)
- [StandardSim: A Synthetic Dataset For Retail Environments](https://mlsanity.com/paper/2202.02418/) (2022)
- [Matching neural paths: transfer from recognition to correspondence search](https://mlsanity.com/paper/1705.08272/) (2017)
- [Spot the Difference by Object Detection](https://mlsanity.com/paper/1801.01051/) (2018)

## Built on by (most cited first, 2 of 2)

- [Zero-Shot Scene Change Detection](https://mlsanity.com/paper/2406.11210/) (2024)
- [STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models](https://mlsanity.com/paper/2510.22571/) (2025)

## Abstract (arXiv)

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.