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

TL;DR

This paper introduces a novel self-attention based method with unsupervised domain adaptation for small object change detection in indoor robot navigation, significantly improving detection performance without extensive retraining.

Contribution

It presents a new attention mask technique that enables unsupervised, on-the-fly domain adaptation for change detection models in robotics applications.

Findings

Significant boost in change detection accuracy.

Effective unsupervised domain adaptation.

Improved detection of small, non-distinctive changes.

Abstract

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.