Papers › GMTR: Graph Matching Transformers

GMTR: Graph Matching Transformers

14 Nov 2023arXiv:2311.08141archive 2025-07-28

Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan

Vision transformers (ViTs) have recently been used for visual matching beyond object detection and segmentation. However, the original grid dividing strategy of ViTs neglects the spatial information of the keypoints, limiting the sensitivity to local information. Therefore, we propose QueryTrans (Query Transformer), which adopts a cross-attention module and keypoints-based center crop strategy for better spatial information extraction. We further integrate the graph attention module and devise a transformer-based graph matching approach GMTR (Graph Matching TRansformers) whereby the combinatorial nature of GM is addressed by a graph transformer neural GM solver. On standard GM benchmarks, GMTR shows competitive performance against the SOTA frameworks. Specifically, on Pascal VOC, GMTR achieves 83.6% accuracy, 0.9% higher than the SOTA framework. On Spair-71k, GMTR shows great potential and outperforms most of the previous works. Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from 80.1% to 83.3%, and BBGM from 79.0% to 84.5%. On Spair-71k, QueryTrans improves NGMv2 from 80.6% to 82.5%, and BBGM from 82.1% to 83.9%. Source code will be made publicly available.

Paper PDF Code

Code

jp-guo/gm-transformer officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph Attention Graph Matching Object Detection object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Graph Matching	PASCAL VOC	GMT-BBGM	matching accuracy	0.8411	#13 of 31	Archive leaderboard	report
Graph Matching	PASCAL VOC	GMTR	matching accuracy	0.836	#14 of 31	Archive leaderboard	report
Graph Matching	SPair-71k	GMTR	matching accuracy	0.832	#3 of 8	Archive leaderboard	report
Graph Matching	SPair-71k	GMT-BBGM	matching accuracy	0.8296	#4 of 8	Archive leaderboard	report
Graph Matching	Willow Object Class	GMT-BBGM	matching accuracy	0.9813	#6 of 23	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Concatenated Skip Connection Dense Connections Dropout Graph Transformer Label Smoothing LapEigen Laplacian PE Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections