Learning Localization-aware Target Confidence for Siamese Visual Tracking. (arXiv:2204.14093v1 [cs.CV])

Siamese tracking paradigm has achieved great success, providing effective
appearance discrimination and size estimation by the classification and
regression. While such a paradigm typically optimizes the classification and
regression independently, leading to task misalignment (accurate prediction
boxes have no high target confidence scores). In this paper, to alleviate this
misalignment, we propose a novel tracking paradigm, called SiamLA. Within this
paradigm, a series of simple, yet effective localization-aware components are
introduced, to generate localization-aware target confidence scores.
Specifically, with the …

arxiv confidence cv learning localization tracking