Efficient Visual Tracking Using Local Information Patch Attention Free Transformer

Pin Feng Wang, Chih Wei Tang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

The state-of-the-art (SOTA) transformer tracker TransT achieves high tracking accuracy. Nevertheless, the time and space complexity of its attention operation is quadratic to the spatial dimension of feature vectors. Thus it is difficult to deploy TransT on resource constrained devices. This paper proposes Local Information Patch Attention Free Transformer (LIP-AFT) based Local Information Patch Self-Attention Free Transformer (LIPS-AFT) and Local Information Patch Cross-Attention Free Transformer (LIPC-AFT) for linear time and space complexity and high accuracy. LIP-AFT benefits from global connectivity between patches while it focuses on naïve strong local attention patterns. The proposed tracker outperforms both SOTA trackers and TransT with various SOTA attention algorithms on accuracy and complexity. Moreover, its inference phase runs at 41 fps on RTX 2070S GPUs.

原文???core.languages.en_GB???
主出版物標題Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面447-448
頁數2
ISBN(電子)9781665470506
DOIs
出版狀態已出版 - 2022
事件2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 - Taipei, Taiwan
持續時間: 6 7月 20228 7月 2022

出版系列

名字Proceedings - 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022
國家/地區Taiwan
城市Taipei
期間6/07/228/07/22

指紋

深入研究「Efficient Visual Tracking Using Local Information Patch Attention Free Transformer」主題。共同形成了獨特的指紋。

引用此