DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking

TL;DR

DeepMix introduces an online data augmentation method using historical sample embeddings to improve visual object tracking accuracy and robustness without sacrificing speed.

Contribution

The paper presents DeepMix, a novel online augmentation approach with MixNet, enhancing existing trackers by generating augmented embeddings in one step.

Findings

Improves tracking accuracy across multiple frameworks.

Effective on large-scale challenging datasets.

Maintains high processing speeds.

Abstract

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.