Leveraging the Power of Data Augmentation for Transformer-based Tracking
This work addresses the need for better training data strategies in visual object tracking, offering incremental improvements for researchers and practitioners in computer vision.
The paper tackles the problem of improving transformer-based visual object tracking by addressing the overlooked role of data augmentation, proposing two customized methods that enhance performance, especially in challenging scenarios like one-shot tracking and small resolutions, with demonstrated effectiveness across multiple benchmarks.
Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance. Previous works focus on designing effective architectures suited for tracking, but ignore that data augmentation is equally crucial for training a well-performing model. In this paper, we first explore the impact of general data augmentations on transformer-based trackers via systematic experiments, and reveal the limited effectiveness of these common strategies. Motivated by experimental observations, we then propose two data augmentation methods customized for tracking. First, we optimize existing random cropping via a dynamic search radius mechanism and simulation for boundary samples. Second, we propose a token-level feature mixing augmentation strategy, which enables the model against challenges like background interference. Extensive experiments on two transformer-based trackers and six benchmarks demonstrate the effectiveness and data efficiency of our methods, especially under challenging settings, like one-shot tracking and small image resolutions.