TapLab A Fast Framework for Semantic Video Segmentation Tapping Into Compressed-Domain Knowledge

TapLab : A Fast Framework for Semantic Video Segmentation Tapping Into Compressed-Domain Knowledge

Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed. Recent approaches mainly devote great efforts to reducing the model size for high efficiency. In this paper, we rethink this problem from a different viewpoint: using knowledge contained in...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 3 vom: 01. März, Seite 1591-1603
1. Verfasser: Feng, Junyi (VerfasserIn)
Weitere Verfasser: Li, Songyuan, Li, Xi, Wu, Fei, Tian, Qi, Yang, Ming-Hsuan, Ling, Haibin
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
Beschreibung
Zusammenfassung:Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed. Recent approaches mainly devote great efforts to reducing the model size for high efficiency. In this paper, we rethink this problem from a different viewpoint: using knowledge contained in compressed videos. We propose a simple and effective framework, dubbed TapLab, to tap into resources from the compressed domain. Specifically, we design a fast feature warping module using motion vectors for acceleration. To reduce the noise introduced by motion vectors, we design a residual-guided correction module and a residual-guided frame selection module using residuals. TapLab significantly reduces redundant computations of the state-of-the-art fast semantic image segmentation models, running 3 to 10 times faster with controllable accuracy degradation. The experimental results show that TapLab achieves 70.6 percent mIoU on the Cityscapes dataset at 99.8 FPS with a single GPU card for the 1024×2048 videos. A high-speed version even reaches the speed of 160+ FPS. Code will be available soon at https://github.com/Sixkplus/TapLab
Beschreibung:Date Revised 04.02.2022
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1939-3539
DOI:10.1109/TPAMI.2020.3024646