Can I read BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation on EtoBox?

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation by Yu, Changqian; Gao, Changxin; Wang, Jingbo; Yu, Gang; Shen, Chunhua; Sang, Nong is a scholarly article available to read on EtoBox.

What is BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation about?

The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable accuracy decrease. We propose to treat these spatial details and categorical semantics separately to achieve high accuracy and high efficiency for realtime semantic segmentation. To this end, we propose an efficient and effective architecture with a good trade-off between speed and accuracy, termed Bilateral Segmentation Network (BiSeNet V2). This architecture involves: (i) a Detail Branch, with wide channels and shallow layers to capture low-level details and generate high-resolution feature representation; (ii) a Semantic Branch, with narrow channels and deep layers to obtain high-level semantic context. The Semantic Branch is lightweight due to reducing the channel capacity and a fast-downsampling strategy. Furthermore, we design a Guided Aggregation Layer to enhance mutual connections and fuse both types of feature representation. Besides, a booster training strategy is designed to improve the segmentation performance without any extra inferen

Author

Yu, Changqian; Gao, Changxin; Wang, Jingbo; Yu, Gang; Shen, Chunhua; Sang, Nong

Published

2020

Language

EN