Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection

Abstract

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the dense prediction as a united and straightforward form of pseudo-label. Compared to the pseudo-boxes, our Dense Pseudo-Label (DPL) does not involve any post-processing method, thus retaining richer information. We also introduce a region selection technique to highlight the key information while suppressing the noise carried by dense labels. We name our proposed SS-OD algorithm that leverages the DPL as Dense Teacher. On COCO and VOC, Dense Teacher shows superior performance under various settings compared with the pseudo-box-based methods. Code will be available.

Cite

Text

Zhou et al. "Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-20077-9_3

Markdown

[Zhou et al. "Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/zhou2022eccv-dense/) doi:10.1007/978-3-031-20077-9_3

BibTeX

@inproceedings{zhou2022eccv-dense,
  title     = {{Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection}},
  author    = {Zhou, Hongyu and Ge, Zheng and Liu, Songtao and Mao, Weixin and Li, Zeming and Yu, Haiyan and Sun, Jian},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2022},
  doi       = {10.1007/978-3-031-20077-9_3},
  url       = {https://mlanthology.org/eccv/2022/zhou2022eccv-dense/}
}