LabelEnc: A New Intermediate Supervision Method for Object Detection

Abstract

In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems. The key idea is to introduce a novel label encoding function, mapping the ground-truth labels into latent embedding, acting as an auxiliary intermediate supervision to the detection backbone during training. Our approach mainly involves a two-step training procedure. First, we optimize the label encoding function via an AutoEncoder defined in the label space, approximating the ""desired"" intermediate representations for the target object detector. Second, taking advantage of the learned label encoding function, we introduce a new auxiliary loss attached to the detection backbones, thus benefiting the performance of the derived detector. Experiments show our method improves a variety of detection systems by around 2% on COCO dataset, no matter one-stage or two-stage frameworks. Moreover, the auxiliary structures only exist during training, i.e. it is completely cost-free in inference time.

Cite

Text

Hao et al. "LabelEnc: A New Intermediate Supervision Method for Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58595-2_32

Markdown

[Hao et al. "LabelEnc: A New Intermediate Supervision Method for Object Detection." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/hao2020eccv-labelenc/) doi:10.1007/978-3-030-58595-2_32

BibTeX

@inproceedings{hao2020eccv-labelenc,
  title     = {{LabelEnc: A New Intermediate Supervision Method for Object Detection}},
  author    = {Hao, Miao and Liu, Yitao and Zhang, Xiangyu and Sun, Jian},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58595-2_32},
  url       = {https://mlanthology.org/eccv/2020/hao2020eccv-labelenc/}
}