Adversarial attack can help visual tracking
- Authors
- Cho, S.; Kim, H.; Kim, J.S.; Kim, H.; Kwon, Junseok
- Issue Date
- Oct-2022
- Publisher
- Springer
- Keywords
- Adversarial Attack; Noise-injected Markov chain Monte Carlo; Visual Tracking
- Citation
- Multimedia Tools and Applications, v.81, no.24, pp 35283 - 35292
- Pages
- 10
- Journal Title
- Multimedia Tools and Applications
- Volume
- 81
- Number
- 24
- Start Page
- 35283
- End Page
- 35292
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/55666
- DOI
- 10.1007/s11042-022-12789-0
- ISSN
- 1380-7501
1432-1882
- Abstract
- We present a novel noise-injected Markov chain Monte Carlo (NMCMC) method for visual tracking, which enables fast convergence through adversarial attacks. The proposed NMCMC consists of three steps: noise-injected proposal, acceptance, and validation. We intentionally inject noise into the proposal function to cause a shift in a direction that is opposite to the moving direction of a target, which is viewed in the context of an adversarial attack. This noise injection mathematically induces the proposed visual tracker to find a target proposal distribution using a small number of samples, which allows the tracker to be robust to drifting. Experimental results demonstrate that our method achieves state-of-the-art performance, especially when severe perturbations caused by an adversarial attack exist in the target state. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.