Towards Sequence-Level Training for Visual Tracking
- Title
- Towards Sequence-Level Training for Visual Tracking
- Authors
- Kim, Minji; Lee, Seungkwan; OK, JUNGSEUL; Han, Bohyung; Cho, Minsu
- Date Issued
- 2022-10-23
- Publisher
- Springer Science and Business Media
- Abstract
- Despite the extensive adoption of machine learning on the task of visual object tracking, recent learning-based approaches have largely overlooked the fact that visual tracking is a sequence-level task in its nature; they rely heavily on frame-level training, which inevitably induces inconsistency between training and testing in terms of both data distributions and task objectives. This work introduces a sequence-level training strategy for visual tracking based on reinforcement learning and discusses how a sequence-level design of data sampling, learning objectives, and data augmentation can improve the accuracy and robustness of tracking algorithms. Our experiments on standard benchmarks including LaSOT, TrackingNet, and GOT-10k demonstrate that four representative tracking models, SiamRPN++, SiamAttn, TransT, and TrDiMP, consistently improve by incorporating the proposed methods in training without modifying architectures.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/114634
- ISSN
- 0302-9743
- Article Type
- Conference
- Citation
- 17th European Conference on Computer Vision, ECCV 2022, page. 534 - 551, 2022-10-23
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.