Author ORCID Identifier
Semester
Spring
Date of Graduation
2025
Document Type
Thesis
Degree Type
MS
College
Statler College of Engineering and Mineral Resources
Department
Lane Department of Computer Science and Electrical Engineering
Committee Chair
Gianfranco Doretto
Committee Co-Chair
Donald Adjeroh
Committee Member
Donald Adjeroh
Committee Member
Prashnna Gyawali
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/.
Recommended Citation
Zaveri, Ram J., "Efficient and Test-Time Adaptive Visual Object Tracking in the Wild" (2025). Graduate Theses, Dissertations, and Problem Reports. 12791.
https://researchrepository.wvu.edu/etd/12791