Improving Accuracy and Generalization for Efficient Visual Tracking

Ram Zaveri, Shivang Patel, Yu Gu, Gianfranco Doretto; Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 2025, pp. 9450-9460

Efficient visual trackers overfit to their training distributions and lack generalization abilities resulting in them performing well on their respective in-distribution (ID) test sets and not as well on out-of-distribution (OOD) sequences imposing limitations to 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. Our code and models are available at https://wvuvl.github.io/SiamABC/.