Group Orthogonal Low-Rank Adaptation for RGB-T Tracking

TL;DR

This paper introduces GOLA, a structured parameter learning framework for RGB-T tracking that reduces redundancy and enhances feature diversity by enforcing orthogonal constraints on rank groups.

Contribution

It proposes a novel group orthogonal low-rank adaptation method that improves parameter efficiency and feature diversity in RGB-T tracking models.

Findings

GOLA outperforms state-of-the-art methods on four benchmark datasets.

It effectively reduces parameter redundancy in RGB-T tracking.

GOLA enhances feature representation capabilities for diverse challenges.

Abstract

Parameter-efficient fine-tuning has emerged as a promising paradigm in RGB-T tracking, enabling downstream task adaptation by freezing pretrained parameters and fine-tuning only a small set of parameters. This set forms a rank space made up of multiple individual ranks, whose expressiveness directly shapes the model's adaptability. However, quantitative analysis reveals low-rank adaptation exhibits significant redundancy in the rank space, with many ranks contributing almost no practical information. This hinders the model's ability to learn more diverse knowledge to address the various challenges in RGB-T tracking. To address this issue, we propose the Group Orthogonal Low-Rank Adaptation (GOLA) framework for RGB-T tracking, which effectively leverages the rank space through structured parameter learning. Specifically, we adopt a rank decomposition partitioning strategy utilizing singular value decomposition to quantify rank importance, freeze crucial ranks to preserve the pretrained priors, and cluster the redundant ranks into groups to prepare for subsequent orthogonal constraints. We further design an inter-group orthogonal constraint strategy. This constraint enforces orthogonality between rank groups, compelling them to learn complementary features that target diverse challenges, thereby alleviating information redundancy. Experimental results demonstrate that GOLA effectively reduces parameter redundancy and enhances feature representation capabilities, significantly outperforming state-of-the-art methods across four benchmark datasets and validating its effectiveness in RGB-T tracking tasks.