The Solution for Single Object Tracking Task of Perception Test Challenge 2024

TL;DR

This paper introduces a novel single object tracking method using LoRA fine-tuning and alpha-refine post-processing, achieving top performance in the 2024 perception test challenge.

Contribution

It adapts LoRA for visual tracking and combines it with alpha-refine, demonstrating a new approach for efficient and effective object tracking.

Findings

Achieved a score of 0.813, securing first place in the challenge.

Demonstrated the effectiveness of LoRA fine-tuning in visual tracking.

Implemented alpha-refine, though with limited success.

Abstract

This report presents our method for Single Object Tracking (SOT), which aims to track a specified object throughout a video sequence. We employ the LoRAT method. The essence of the work lies in adapting LoRA, a technique that fine-tunes a small subset of model parameters without adding inference latency, to the domain of visual tracking. We train our model using the extensive LaSOT and GOT-10k datasets, which provide a solid foundation for robust performance. Additionally, we implement the alpha-refine technique for post-processing the bounding box outputs. Although the alpha-refine method does not yield the anticipated results, our overall approach achieves a score of 0.813, securing first place in the competition.