A Discriminative Single-Shot Segmentation Network for Visual Object Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence(2022)
摘要
Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of transformation models, which reduces their localization accuracy. We propose a discriminative single-shot segmentation tracker – D3S
$_2$
, which narrows the gap between visual object tracking and video object segmentation. A single-shot network applies two target models with complementary geometric properties, one invariant to a broad range of transformations, including non-rigid deformations, the other assuming a rigid object to simultaneously achieve robust online target segmentation. The overall tracking reliability is further increased by decoupling the object and feature scale estimation. Without per-dataset finetuning, and trained only for segmentation as the primary output, D3S
$_2$
outperforms all published trackers on the recent short-term tracking benchmark VOT2020 and performs very close to the state-of-the-art trackers on the GOT-10k, TrackingNet, OTB100 and LaSoT. D3S
$_2$
outperforms the leading segmentation tracker SiamMask on video object segmentation benchmarks and performs on par with top video object segmentation algorithms.
更多查看译文
关键词
Visual object tracking,video object segmentation,discriminative tracking,single-shot segmentation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要