Pyramid Correlation based Deep Hough Voting for Visual Object Tracking

Ying Wang, Tingfa Xu*, Jianan Li*, Shenwang Jiang, Junjie Chen

*此作品的通讯作者

科研成果: 期刊稿件会议文章同行评审

2 引用 (Scopus)

摘要

Most of the existing Siamese-based trackers treat tracking problem as a parallel task of classification and regression. However, some studies show that the sibling head structure could lead to suboptimal solutions during the network training. Through experiments we find that, without regression, the performance could be equally promising as long as we delicately design the network to suit the training objective. We introduce a novel voting-based classification-only tracking algorithm named Pyramid Correlation based Deep Hough Voting (short for PCDHV), to jointly locate the top-left and bottom-right corners of the target. Specifically we innovatively construct a Pyramid Correlation module to equip the embedded feature with fine-grained local structures and global spatial contexts; The elaborately designed Deep Hough Voting module further take over, integrating long-range dependencies of pixels to perceive corners; In addition, the prevalent discretization gap is simply yet effectively alleviated by increasing the spatial resolution of the feature maps while exploiting channel-space relationships. The algorithm is general, robust and simple. We demonstrate the effectiveness of the module through a series of ablation experiments. Without bells and whistles, our tracker achieves better or comparable performance to the SOTA algorithms on three challenging benchmarks (TrackingNet, GOT-10k and LaSOT) while running at a real-time speed of 80 FPS. Codes and models will be released.

源语言英语
页(从-至)610-625
页数16
期刊Proceedings of Machine Learning Research
157
出版状态已出版 - 2021
活动13th Asian Conference on Machine Learning, ACML 2021 - Virtual, Online
期限: 17 11月 202119 11月 2021

指纹

探究 'Pyramid Correlation based Deep Hough Voting for Visual Object Tracking' 的科研主题。它们共同构成独一无二的指纹。

引用此