TY - GEN
T1 - Automatic Network Architecture Search for RGB-D Semantic Segmentation
AU - Wang, Wenna
AU - Zhuo, Tao
AU - Zhang, Xiuwei
AU - Sun, Mingjun
AU - Yin, Hanlin
AU - Xing, Yinghui
AU - Zhang, Yanning
N1 - Publisher Copyright:
© 2023 ACM.
PY - 2023/10/26
Y1 - 2023/10/26
N2 - 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.
AB - 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.
KW - grid-like network-level search space
KW - hierarchical cell-level search space
KW - nas
KW - rgb-d semantic segmentation
KW - search strategy
UR - http://www.scopus.com/inward/record.url?scp=85179552857&partnerID=8YFLogxK
U2 - 10.1145/3581783.3612288
DO - 10.1145/3581783.3612288
M3 - 会议稿件
AN - SCOPUS:85179552857
T3 - MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia
SP - 3777
EP - 3786
BT - MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia
PB - Association for Computing Machinery, Inc
T2 - 31st ACM International Conference on Multimedia, MM 2023
Y2 - 29 October 2023 through 3 November 2023
ER -