DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking
arXiv:2104.11585
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.
arXiv comment6 pages, 2 figures. This work has been accepted to ICME 2021
References in corpus (11)
- High-Speed Tracking with Kernelized Correlation Filters
- mixup: Beyond Empirical Risk Minimization
- On Calibration of Modern Neural Networks
- AutoAugment: Learning Augmentation Policies from Data
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
- Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
- Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking
- Fully-Convolutional Siamese Networks for Object Tracking
- Bias Field Poses a Threat to DNN-based X-Ray Recognition
- Auto-Exposure Fusion for Single-Image Shadow Removal