MatchDet: A Collaborative Framework for Image Matching and Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Jinxiang, Wu, Wenlong, Gao, Bin-Bin, Liu, Jun, Zhan, Jiawei, Nie, Congchong, Zeng, Yi, Wang, Chengjie
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929423236726784
author Lai, Jinxiang
Wu, Wenlong
Gao, Bin-Bin
Liu, Jun
Zhan, Jiawei
Nie, Congchong
Zeng, Yi
Wang, Chengjie
author_facet Lai, Jinxiang
Wu, Wenlong
Gao, Bin-Bin
Liu, Jun
Zhan, Jiawei
Nie, Congchong
Zeng, Yi
Wang, Chengjie
contents Image matching and object detection are two fundamental and challenging tasks, while many related applications consider them two individual tasks (i.e. task-individual). In this paper, a collaborative framework called MatchDet (i.e. task-collaborative) is proposed for image matching and object detection to obtain mutual improvements. To achieve the collaborative learning of the two tasks, we propose three novel modules, including a Weighted Spatial Attention Module (WSAM) for Detector, and Weighted Attention Module (WAM) and Box Filter for Matcher. Specifically, the WSAM highlights the foreground regions of target image to benefit the subsequent detector, the WAM enhances the connection between the foreground regions of pair images to ensure high-quality matches, and Box Filter mitigates the impact of false matches. We evaluate the approaches on a new benchmark with two datasets called Warp-COCO and miniScanNet. Experimental results show our approaches are effective and achieve competitive improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2312_10983
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MatchDet: A Collaborative Framework for Image Matching and Object Detection
Lai, Jinxiang
Wu, Wenlong
Gao, Bin-Bin
Liu, Jun
Zhan, Jiawei
Nie, Congchong
Zeng, Yi
Wang, Chengjie
Computer Vision and Pattern Recognition
Image matching and object detection are two fundamental and challenging tasks, while many related applications consider them two individual tasks (i.e. task-individual). In this paper, a collaborative framework called MatchDet (i.e. task-collaborative) is proposed for image matching and object detection to obtain mutual improvements. To achieve the collaborative learning of the two tasks, we propose three novel modules, including a Weighted Spatial Attention Module (WSAM) for Detector, and Weighted Attention Module (WAM) and Box Filter for Matcher. Specifically, the WSAM highlights the foreground regions of target image to benefit the subsequent detector, the WAM enhances the connection between the foreground regions of pair images to ensure high-quality matches, and Box Filter mitigates the impact of false matches. We evaluate the approaches on a new benchmark with two datasets called Warp-COCO and miniScanNet. Experimental results show our approaches are effective and achieve competitive improvements.
title MatchDet: A Collaborative Framework for Image Matching and Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.10983