HoloSeg: An Efficient Holographic Segmentation Network for Real-time Scene Parsing

Shu Li, Qingqing Yan, Chengju Liu, Ming Liu, Qijun ChenICRA 2022 · OpenReview

Abstract

Real-time semantic segmentation is a crucial but challenging dense prediction task for scene parsing. However, the existing CNN-based methods commonly bias the model in favor of speed-boosting compromising spatial resolution due to business requirements and hardware constrains, which impedes the high-accuracy segmentation result. To address the dilemma, we provide a novel Holographic Segmentation Network (HoloSeg), which presents a strong ability of comprehensive information preservation and extraction, and achieves a better trade-off between speed and accuracy. We first design a Lossless Sample Pair (LSP) without any stride for early spatial preservation and later resolution recovery while modeling long-range context dependence. Then, we propose Distributed Pyramid Learning (DPL) to efficiently extract multiscale features and saves a lot of computation. Finally, we propose Resolution Fusion and Restoration (RFR) to fuse multi-level semantic representations across stages and generate output without decoder. Without bells and whistles, HoloSeg achieves state-of-the-art performance on the Cityscapes benchmark which reports 76.24% mIoU at 231 FPS. Code is available online: https://github.com/LiShuTJ/HoloSeg.
BibTeX
@inproceedings{li2022holoseg,
  author = {Shu Li and Qingqing Yan and Chengju Liu and Ming Liu and Qijun Chen},
  title = {{HoloSeg: An Efficient Holographic Segmentation Network for Real-time Scene Parsing}},
  booktitle = {IEEE International Conference on Robotics and Automation},
  year = {2022},
  url = {https://openreview.net/forum?id=ndP5Kwulpe},
}

Loading related content...

Figure