Related papers: Learning Localization-aware Target Confidence for Siamese Visual Tracking

Learning Localization-aware Target Confidence for Siamese Visual Tracking

URL: http://arxiv.org/abs/2204.14093v1
Date: Fri, 29 Apr 2022 13:37:15 GMT
Title: Learning Localization-aware Target Confidence for Siamese Visual Tracking
Authors: Jiahao Nie, Han Wu, Zhiwei He, Yuxiang Yang, Mingyu Gao, Zhekang Dong
Abstract summary: We propose a novel tracking paradigm, called SiamLA. Within this paradigm, a series of simple, yet effective localization-aware components are introduced. Our SiamLA achieves state-of-the-art performance in terms of both accuracy and efficiency.
Score: 13.684278662495204
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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 proposed localization-aware dynamic label (LADL) loss and localization-aware label smoothing (LALS) strategy, collaborative optimization between the classification and regression is achieved, enabling classification scores to be aware of location state, not just appearance similarity. Besides, we propose a separate localization branch, centered on a localization-aware feature aggregation (LAFA) module, to produce location quality scores to further modify the classification scores. Consequently, the resulting target confidence scores, are more discriminative for the location state, allowing accurate prediction boxes tend to be predicted as high scores. Extensive experiments are conducted on six challenging benchmarks, including GOT-10k, TrackingNet, LaSOT, TNL2K, OTB100 and VOT2018. Our SiamLA achieves state-of-the-art performance in terms of both accuracy and efficiency. Furthermore, a stability analysis reveals that our tracking paradigm is relatively stable, implying the paradigm is potential to real-world applications.