Back to search

West Virginia University

Efficient and Test-Time Adaptive Visual Object Tracking in the Wild

Abstract

dc:description.abstract

Tracking a single object, given the location at the first frame, has been an ongoing challenge in the vision community for decades. Most recent approaches provide reasonably good performance, especially when benchmarked on in-distribution (ID) datasets, i.e., on the testing portion of the same datasets used for training. However, they incur high computational costs and hardware constraints, making their deployment in the wild for mobile, autonomous, and IoT applications still challenging. Efficient visual trackers address the efficiency aspect of such bottlenecks; however, they tend to overfit to their training distributions and lack generalization abilities, resulting in them performing well on their respective in-distribution (ID) test sets but not as well on out-of-distribution (OOD) sequences, which again imposes limitations on their deployment in the wild under constrained resources. We introduce SiamABC, a highly efficient Siamese tracker that significantly improves tracking performance, even on OOD sequences. SiamABC takes advantage of new architectural designs in the way it bridges the dynamic variability of the target, and of new losses for training. Also, it directly addresses OOD tracking generalization by including a fast backward-free dynamic test-time adaptation method that continuously adapts the model according to the dynamic visual changes of the target. Our extensive experiments suggest that SiamABC shows remarkable performance gains in OOD sets while maintaining accurate performance on the ID benchmarks. SiamABC outperforms MixFormerV2-S by 7.6% on the OOD AVisT benchmark while being 3x faster (100 FPS) on a CPU. We also contribute by making the codebase publicly available at https://wvuvl.github.io/SiamABC/.

Degree

thesis:*
Name thesis:degree_name
MS
Level thesis:degree_level
Thesis
Discipline thesis:degree_discipline
Lane Department of Computer Science and Electrical Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zaveri, Ram J.
Contributors dc:contributor
  • Gianfranco Doretto
  • Donald Adjeroh
  • Prashnna Gyawali

Subjects

dc:subject × 8

Identifiers

dc:identifier.*
Identifier
<p><a href="https://orcid.org/0000-0002-1805-7967">https://orcid.org0000-0002-1805-7967</a></p>
https://researchrepository.wvu.edu/etd/12791

Chain of custody

source
Harvested from
West Virginia University
Base URL
researchrepository.wvu.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Zaveri, Ram J.. Efficient and Test-Time Adaptive Visual Object Tracking in the Wild. Thesis thesis, https://doi.org/10.33915/etd.12791