SiamCAN:Simple yet Effective Method to enhance Siamese Short-Term Tracking

Yue Zhao, Zhibin Yu

Keywords: Siamese trackers, cross-attention, light structure, anchor-free

Abstract: Most traditional Siamese trackers are used to regard the location of the max response map as the center of target. However, it is difficult for these traditional methods to calculate response value accurately when face the similar object, deformation, background clutters and other challenges. So how to get the reliable response map is the key to improve tracking performance. Accordingly, a simple yet effective short-term tracking framework (called SiamCAN),by which bridging the information flow between search branch and template branch, is proposed to solve the above problem in this paper. Moreover, in order to get more accurate target estimation, an anchor-free mechanism and specialized training strategy are applied to narrow the gap between the predicted bounding box and groundtruth. The proposed method achieves state-of-the-art performance on four visual tracking benchmarks including UAV123, OTB100, VOT2018 and VOT2019, outperforming the strong baseline, SiamBAN, by 0.327 $\displaystyle \rightarrow$ 0.331 on VOT2019 and 0.631 $\displaystyle \rightarrow$ 0.638 success score, 0.833 $\displaystyle \rightarrow$ 0.850 precision score on UAV123.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose a series of simple yet effective method for Siamese trackers to solve similar distractor, scale variation and background clutters challenge.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=C0sLQsZF-s