# Domain Invariant Siamese Attention Mask for Small Object Change Detection via Everyday Indoor Robot Navigation

arXiv: https://arxiv.org/abs/2203.15362 · HTML: https://mlsanity.com/paper/2203.15362/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 29 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [Anomaly Detection in Video Sequence with Appearance-Motion Correspondence](https://mlsanity.com/paper/1908.06351/) (2019)
- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images](https://mlsanity.com/paper/2003.03608/) (2020)
- [Weakly Supervised Silhouette-based Semantic Scene Change Detection](https://mlsanity.com/paper/1811.11985/) (2018)
- [PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation](https://mlsanity.com/paper/2101.06175/) (2021)
- [DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection](https://mlsanity.com/paper/2103.00879/) (2021)
- [Hierarchical Paired Channel Fusion Network for Street Scene Change Detection](https://mlsanity.com/paper/2010.09925/) (2020)
- [Dense Optical Flow based Change Detection Network Robust to Difference of Camera Viewpoints](https://mlsanity.com/paper/1712.02941/) (2017)

## Built on by (most cited first, 3 of 3)

- [Self-Calibrating Anomaly and Change Detection for Autonomous Inspection Robots](https://mlsanity.com/paper/2209.02379/) (2022)
- [Zero-shot Degree of Ill-posedness Estimation for Active Small Object Change Detection](https://mlsanity.com/paper/2405.06185/) (2024)
- [Dynamic-Dark SLAM: RGB-Thermal Cooperative Robot Vision Strategy for Multi-Person Tracking in Both Well-Lit and Low-Light Scenes](https://mlsanity.com/paper/2503.12768/) (2025)

## Abstract (arXiv)

The problem of image change detection via everyday indoor robot navigation is explored from a novel perspective of the self-attention technique. Detecting semantically non-distinctive and visually small changes remains a key challenge in the robotics community. Intuitively, these small non-distinctive changes may be better handled by the recent paradigm of the attention mechanism, which is the basic idea of this work. However, existing self-attention models require significant retraining cost per domain, so it is not directly applicable to robotics applications. We propose a new self-attention technique with an ability of unsupervised on-the-fly domain adaptation, which introduces an attention mask into the intermediate layer of an image change detection model, without modifying the input and output layers of the model. Experiments, in which an indoor robot aims to detect visually small changes in everyday navigation, demonstrate that our attention technique significantly boosts the state-of-the-art image change detection model.