paper-with-me

홈 › Papers

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

2022-03-29 · Koji Takeda, Kanji Tanaka, Yoshimasa Nakamura

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.

📄 PDF Abstract BibTeX arXiv:2203.15362

Code (0)

등록된 구현이 없습니다.

Tasks

Change DetectionDomain AdaptationRobot Navigation

Similar Papers 제목 키워드 기반

Masked Siamese ConvNets

2022-06-15 · Li Jing, Jiachen Zhu, Yann Lecun

Self-supervised learning has shown superior performances over supervised methods on various vision benchmarks. The siamese network, which encourages embeddings to be invariant to distortions, is one of the most successfu…

image-classificationImage ClassificationInductive Biasobject-detection+3

Understanding Masked Image Modeling via Learning Occlusion Invariant Feature

2022-08-08 · CVPR 2023 1 · Xiangwen Kong, Xiangyu Zhang

Recently, Masked Image Modeling (MIM) achieves great success in self-supervised visual recognition. However, as a reconstruction-based framework, it is still an open question to understand how MIM works, since MIM appear…

Contrastive LearningOpen-Ended Question Answering

TINYCD: A (Not So) Deep Learning Model For Change Detection

2022-07-26 · Andrea Codegoni, Gabriele Lombardi, Alessandro Ferrari

In this paper, we present a lightweight and effective change detection model, called TinyCD. This model has been designed to be faster and smaller than current state-of-the-art change detection models due to industrial n…

Building change detection for remote sensing imagesChange DetectionChange detection for remote sensing imagesDeep Learning

Re-Identification with Consistent Attentive Siamese Networks

2018-11-19 · CVPR 2019 6 · Meng Zheng, Srikrishna Karanam, Ziyan Wu, Richard J. Radke

We propose a new deep architecture for person re-identification (re-id). While re-id has seen much recent progress, spatial localization and view-invariant representation learning for robust cross-view matching remain ke…

Person Re-IdentificationRepresentation Learning

Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search

2023-02-09 · Jiabei Wang, Yanwei Pang, Jiale Cao, Hanqing Sun 외

Weakly supervised person search aims to perform joint pedestrian detection and re-identification (re-id) with only person bounding-box annotations. Recently, the idea of contrastive learning is initially applied to weakl…

Contrastive LearningPedestrian DetectionPerson Search