Papers › Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking
Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking
Andong Lu, Yuanzhi Guo, Wanyu Wang, Chenglong Li, Jin Tang, Bin Luo
Current RGBT tracking methods often overlook the impact of fusion location on mitigating modality gap, which is key factor to effective tracking. Our analysis reveals that shallower fusion yields smaller distribution gap. However, the limited discriminative power of shallow networks hard to distinguish task-relevant information from noise, limiting the potential of pixel-level fusion. To break shallow limits, we propose a novel \textbf{T}ask-driven \textbf{P}ixel-level \textbf{F}usion network, named \textbf{TPF}, which unveils the power of pixel-level fusion in RGBT tracking through a progressive learning framework. In particular, we design a lightweight Pixel-level Fusion Adapter (PFA) that exploits Mamba's linear complexity to ensure real-time, low-latency RGBT tracking. To enhance the fusion capabilities of the PFA, our task-driven progressive learning framework first utilizes adaptive multi-expert distillation to inherits fusion knowledge from state-of-the-art image fusion models, establishing robust initialization, and then employs a decoupled representation learning scheme to achieve task-relevant information fusion. Moreover, to overcome appearance variations between the initial template and search frames, we presents a nearest-neighbor dynamic template updating scheme, which selects the most reliable frame closest to the current search frame as the dynamic template. Extensive experiments demonstrate that TPF significantly outperforms existing most of advanced trackers on four public RGBT tracking datasets. The code will be released upon acceptance.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Rgb-T Tracking | GTOT | TPF | Precision | 94.3 | #2 of 15 | Archive leaderboard | report |
| Rgb-T Tracking | GTOT | TPF | Success | 76.3 | #2 of 15 | Archive leaderboard | report |
| Rgb-T Tracking | LasHeR | TPF | Precision | 75.1 | #6 of 39 | Archive leaderboard | report |
| Rgb-T Tracking | LasHeR | TPF | Success | 59.5 | #6 of 39 | Archive leaderboard | report |
| Rgb-T Tracking | RGBT210 | TPF | Precision | 88.0 | #4 of 19 | Archive leaderboard | report |
| Rgb-T Tracking | RGBT210 | TPF | Success | 63.8 | #4 of 19 | Archive leaderboard | report |
| Rgb-T Tracking | RGBT234 | TPF | Precision | 89.7 | #13 of 42 | Archive leaderboard | report |
| Rgb-T Tracking | RGBT234 | TPF | Success | 67.1 | #13 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
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