SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Zhengze, Wu, Dongyue, Yu, Changqian, Chu, Xiangxiang, Sang, Nong, Gao, Changxin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910297733726208
author Xu, Zhengze
Wu, Dongyue
Yu, Changqian
Chu, Xiangxiang
Sang, Nong
Gao, Changxin
author_facet Xu, Zhengze
Wu, Dongyue
Yu, Changqian
Chu, Xiangxiang
Sang, Nong
Gao, Changxin
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2312_17071
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
Xu, Zhengze
Wu, Dongyue
Yu, Changqian
Chu, Xiangxiang
Sang, Nong
Gao, Changxin
Computer Vision and Pattern Recognition
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
title SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.17071