Papers › From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and...

From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and Knowledge Distillation

25 Mar 2024arXiv:2403.16834archive 2025-07-28

Yang Luo, Xiqing Guo, Hao Li

Due to the complementary nature of visible light and thermal infrared modalities, object tracking based on the fusion of visible light images and thermal images (referred to as RGB-T tracking) has received increasing attention from researchers in recent years. How to achieve more comprehensive fusion of information from the two modalities at a lower cost has been an issue that researchers have been exploring. Inspired by visual prompt learning, we designed a novel two-stream RGB-T tracking architecture based on cross-modal mutual prompt learning, and used this model as a teacher to guide a one-stream student model for rapid learning through knowledge distillation techniques. Extensive experiments have shown that, compared to similar RGB-T trackers, our designed teacher model achieved the highest precision rate, while the student model, with comparable precision rate to the teacher model, realized an inference speed more than three times faster than the teacher model.(Codes will be available if accepted.)

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

Knowledge DistillationObject TrackingPrompt LearningRgb-T Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Rgb-T Tracking GTOT MMMP Precision 92.4 #6 of 15 Archive leaderboard report
Rgb-T Tracking GTOT MMMP Success 77.3 #6 of 15 Archive leaderboard report
Rgb-T Tracking LasHeR MMMP Precision 71.4 #19 of 39 Archive leaderboard report
Rgb-T Tracking LasHeR MMMP Success 56.7 #19 of 39 Archive leaderboard report
Rgb-T Tracking RGBT234 MMMP Precision 87.3 #23 of 42 Archive leaderboard report
Rgb-T Tracking RGBT234 MMMP Success 65.1 #23 of 42 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

Knowledge DistillationSPEED

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