Papers › Multimodality Adaptive Transformer and Mutual Learning for Unsupervised Domain...

Multimodality Adaptive Transformer and Mutual Learning for Unsupervised Domain Adaptation Vehicle Re-Identification

17 Sep 2024IEEE Transactions on Intelligent Transportation Systems 2024 9archive 2025-07-28

Xin Zhang, Yunan Ling, Kaige Li, Weimin Shi, Zhong Zho

Unsupervised Domain Adaptation Vehicle Re-Identification (UDA vehicle re-ID) aims to enable the model trained in the source domain dataset to adapt to the target domain data and obtain accurate re-identification results, which has received widespread attention due to its practicality in the field of intelligent transportation systems. Most current UDA vehicle re-ID research ignores the mining and utilization of attribute information. Meanwhile, the Convolutional Neural Networks-based (CNN-based) network will cause the loss of fine-grained information, reducing the expression and generalization ability of vehicle features. To alleviate such issues, we are motivated by the Transformer, which can exploit distinguishable attribute information and fuse multimodal features effectively. Therefore, this paper proposes a Multimodality Adaptive Transformer Network (MATNet) to intensify the ability to learn vehicle fine-grained features related to attributes. Moreover, the noise contained in pseudo-labels assigned by cluster algorithms interferes with the performance of the UDA vehicle re-ID method. We also design the Dual Mutual Dynamic Update Pseudo-Label generation strategy (DMDU) to improve the accuracy of pseudo-labels and alleviate error accumulation. The strategy is based on mutual learning, which can effectively utilize the congruous and particular knowledge of the two models to generate pseudo-labels. Extensive experiments on two large-scale public datasets, including VeRi-776 and VehicleID, illustrate that our method outperforms the state-of-the-art methods.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

AttributeDomain AdaptationPseudo LabelUnsupervised Domain AdaptationVehicle Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation VehicleID to VeRi-776 MATNet+DMDU Rank-1 79.13 #2 of 14 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 MATNet+DMDU Rank-10 - #2 of 14 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 MATNet+DMDU Rank-5 88.97 #2 of 14 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 MATNet+DMDU mAP 49.25 #2 of 14 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Large DMDU R-1 47.59 #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Large DMDU R-10 - #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Large DMDU R-5 61.85 #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Large DMDU mAP 53.97 #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Medium DMDU R-1 53.28 #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Medium DMDU R-10 - #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Medium DMDU R-5 63.56 #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Medium DMDU mAP 56.73 #3 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Small DMDU mAP 61.83 #3 of 8 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Small DMDU R-1 55.61 #3 of 8 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Small DMDU R-10 - #3 of 8 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Small DMDU R-5 68.25 #3 of 8 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 EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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