DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking
This work addresses a key bottleneck in visual object tracking by enhancing sample diversity for online learning, though it is incremental as it builds on existing tracking frameworks.
The paper tackles the problem of limited training samples for online object model updating in visual object tracking by proposing DeepMix, an online auto data augmentation method that generates augmented embeddings from historical samples. The method improves tracking accuracy while maintaining speed, achieving performance gains on multiple tracking frameworks and datasets.
Online updating of the object model via samples from historical frames is of great importance for accurate visual object tracking. Recent works mainly focus on constructing effective and efficient updating methods while neglecting the training samples for learning discriminative object models, which is also a key part of a learning problem. In this paper, we propose the DeepMix that takes historical samples' embeddings as input and generates augmented embeddings online, enhancing the state-of-the-art online learning methods for visual object tracking. More specifically, we first propose the online data augmentation for tracking that online augments the historical samples through object-aware filtering. Then, we propose MixNet which is an offline trained network for performing online data augmentation within one-step, enhancing the tracking accuracy while preserving high speeds of the state-of-the-art online learning methods. The extensive experiments on three different tracking frameworks, i.e., DiMP, DSiam, and SiamRPN++, and three large-scale and challenging datasets, \ie, OTB-2015, LaSOT, and VOT, demonstrate the effectiveness and advantages of the proposed method.