iNAS: Integral NAS for Device-Aware Salient Object Detection

Yuchao Gu, Shang-Hua Gao, Xu-Sheng Cao, Peng Du, Shao-Ping Lu, Ming-Ming Cheng

Abstract

Existing salient object detection (SOD) models usually focus on either backbone feature extractors or saliency heads, ignoring their relations. A powerful backbone could still achieve sub-optimal performance with a weak saliency head and vice versa. Moreover, the balance between model performance and inference latency poses a great challenge to model design, especially when considering different deployment scenarios. Considering all components in an integral neural architecture search (iNAS) space, we propose a flexible device-aware search scheme that only trains the SOD model once and quickly finds high-performance but low-latency models on multiple devices. An evolution search with latency-group sampling (LGS) is proposed to explore the entire latency area of our enlarged search space. Models searched by iNAS achieve similar performance with SOTA methods but reduce the 3.8×, 3.3×, 2.6×, 1.9× latency on Huawei Nova6 SE, Intel Core CPU, the Jetson Nano, and Nvidia Titan Xp. The code is released at https://mmcheng.net/inas/.
BibTeX
@inproceedings{gu2021inas,
  author = {Yuchao Gu and Shang-Hua Gao and Xu-Sheng Cao and Peng Du and Shao-Ping Lu and Ming-Ming Cheng},
  title = {{iNAS: Integral NAS for Device-Aware Salient Object Detection}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2021},
  doi = {10.1109/iccv48922.2021.00489},
}

Loading related content...

Figure