Can I read Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking on EtoBox?

Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking by Lu, Andong; Guo, Yuanzhi; Wang, Wanyu; Li, Chenglong; Tang, Jin; Luo, Bin is a scholarly article available to read on EtoBox.

What is Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking about?

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 ini

Author

Lu, Andong; Guo, Yuanzhi; Wang, Wanyu; Li, Chenglong; Tang, Jin; Luo, Bin

Published

2025

Language

EN