Automatic Network Architecture Search for RGB-D Semantic Segmentation

Wenna Wang, Tao Zhuo, Xiuwei Zhang, Mingjun Sun, Hanlin Yin, Yinghui Xing, Yanning Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Recent RGB-D semantic segmentation networks are usually manually designed. However, due to limited human efforts and time costs, their performance might be inferior for complex scenarios. To address this issue, we propose the first Neural Architecture Search (NAS) method that designs the network automatically. Specifically, the target network consists of an encoder and a decoder. The encoder is designed with two independent branches, where each branch specializes in extracting features from RGB and depth images, respectively. The decoder fuses the features and generates the final segmentation result. Besides, for automatic network design, we design a grid-like network-level search space combined with a hierarchical cell-level search space. By further developing an effective gradient-based search strategy, the network structure with hierarchical cell architectures is discovered. Extensive results on two datasets show that the proposed method outperforms the state-of-the-art approaches, which achieves a mIoU score of 55.1% on the NYU-Depth v2 dataset and 50.3% on the SUN-RGBD dataset.

Original languageEnglish
Title of host publicationMM 2023 - Proceedings of the 31st ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages3777-3786
Number of pages10
ISBN (Electronic)9798400701085
DOIs
StatePublished - 26 Oct 2023
Event31st ACM International Conference on Multimedia, MM 2023 - Ottawa, Canada
Duration: 29 Oct 20233 Nov 2023

Publication series

NameMM 2023 - Proceedings of the 31st ACM International Conference on Multimedia

Conference

Conference31st ACM International Conference on Multimedia, MM 2023
Country/TerritoryCanada
CityOttawa
Period29/10/233/11/23

Keywords

  • grid-like network-level search space
  • hierarchical cell-level search space
  • nas
  • rgb-d semantic segmentation
  • search strategy

Fingerprint

Dive into the research topics of 'Automatic Network Architecture Search for RGB-D Semantic Segmentation'. Together they form a unique fingerprint.

Cite this