SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 6378-6386
DOI: 10.1609/aaai.v38i6.28457 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Zhengze Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 188-mal zitiert (Crossref).
Abstract (Originalsprache)
Recent real-time semantic segmentation methods usually adopt an additional semantic branch to pursue rich long-range context. However, the additional branch incurs undesirable computational overhead and slows inference speed. To eliminate this dilemma, we propose SCTNet, a single branch CNN with transformer semantic information for real-time segmentation. SCTNet enjoys the rich semantic representations of an inference-free semantic branch while retaining the high efficiency of lightweight single branch CNN. SCTNet utilizes a transformer as the training-only semantic branch considering its superb ability to extract long-range context. With the help of the proposed transformer-like CNN block CFBlock and the semantic information alignment module, SCTNet could capture the rich semantic information from the transformer branch in training. During the inference, only the single branch CNN needs to be deployed. We conduct extensive experiments on Cityscapes, ADE20K, and COCO-Stuff-10K, and the results show that our method achieves the new state-of-the-art performance. The code and model is available at https://github.com/xzz777/SCTNet.
Zitieren
APA
Xu, Z., Wu, D., Yu, C., Chu, X., Sang, N., & Gao, C. (2024). SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6378-6386. https://doi.org/10.1609/aaai.v38i6.28457
Vancouver
Xu Z, Wu D, Yu C, Chu X, Sang N, Gao C. SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):6378-6386. doi:10.1609/aaai.v38i6.28457
BibTeX
@article{Xu2024,
author = {Xu, Zhengze and Wu, Dongyue and Yu, Changqian and Chu, Xiangxiang and Sang, Nong and Gao, Changxin},
title = {SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {6378--6386},
doi = {10.1609/aaai.v38i6.28457}
}
EUVIMED