Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation

Shu Liu, Xiaojuan Qi, Jianping Shi, Hong Zhang, Jiaya Jia

CVPR 2016

doi:10.1109/CVPR.2016.342 /cvpr/2016/liu2016cvpr-multiscale/

Abstract

Aiming at simultaneous detection and segmentation (SDS), we propose a proposal-free framework, which detect and segment object instances via mid-level patches. We design a unified trainable network on patches, which is followed by a fast and effective patch aggregation algorithm to infer object instances. Our method benefits from end-to-end training. Without object proposal generation, computation time can also be reduced. In experiments, our method yields results 62.1% and 61.8% in terms of mAPr on VOC2012 segmentation val and VOC2012 SDS val, which are state-of-the-art at the time of submission. We also report results on Microsoft COCO test-std/test-dev dataset in this paper.

PDF CVPR Semantic Scholar

Cite

Text

Liu et al. "Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.342

Markdown

[Liu et al. "Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/liu2016cvpr-multiscale/) doi:10.1109/CVPR.2016.342

BibTeX

@inproceedings{liu2016cvpr-multiscale,
  title     = {{Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation}},
  author    = {Liu, Shu and Qi, Xiaojuan and Shi, Jianping and Zhang, Hong and Jia, Jiaya},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2016},
  doi       = {10.1109/CVPR.2016.342},
  url       = {https://mlanthology.org/cvpr/2016/liu2016cvpr-multiscale/}
}