ML Anthology

Pseudo-Label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection

Jun Yu, Liwen Zhang, Shenshen Du, Hao Chang, Keda Lu, Zhong Zhang, Ye Yu, Lei Wang, Qiang Ling
CVPRW 2022 pp. 304-311
doi:10.1109/CVPRW56347.2022.00045 /cvprw/2022/yu2022cvprw-pseudolabel/

Abstract

Semi-supervised learning is a highly researched problem, but existing semi-supervised object detection frameworks are based on RGB images, and existing pre-trained models cannot be used for hyperspectral images. To overcome these difficulties, this paper first select fewer but suitable data augmentation methods to improve the accuracy of the supervised model based on the labeled training set, which is suitable for the characteristics of hyperspectral images. Next, in order to make full use of the unlabeled training set, we generate pseudo-labels with the model trained in the first stage and mix the obtained pseudo-labels with the labeled training set. Then, a large number of strong data augmentation methods are added to make the final model better. We achieve the SOTA, with an AP of 26.35, on the Semi-Supervised Hyperspectral Object Detection Challenge (SSHODC) in the CVPR 2022 Perception Beyond the Visible Spectrum Workshop, and win the first place in this Challenge.

CVPRW Semantic Scholar

Cite

Text

Yu et al. "Pseudo-Label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00045

Markdown

[Yu et al. "Pseudo-Label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/yu2022cvprw-pseudolabel/) doi:10.1109/CVPRW56347.2022.00045

BibTeX

@inproceedings{yu2022cvprw-pseudolabel,
  title     = {{Pseudo-Label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection}},
  author    = {Yu, Jun and Zhang, Liwen and Du, Shenshen and Chang, Hao and Lu, Keda and Zhang, Zhong and Yu, Ye and Wang, Lei and Ling, Qiang},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {304-311},
  doi       = {10.1109/CVPRW56347.2022.00045},
  url       = {https://mlanthology.org/cvprw/2022/yu2022cvprw-pseudolabel/}
}