Switchable K-class Hyperplanes for Noise-Robust Representation Learning

Boxiao Liu, Guanglu Song, Manyuan Zhang, Haihang You, Yu Liu

Abstract

Optimizing the K-class hyperplanes in the latent space has become the standard paradigm for efficient representation learning. However, it’s almost impossible to find an optimal K-class hyperplane to accurately describe the latent space of massive noisy data. For this potential problem, we constructively propose a new method, named Switchable K-class Hyperplanes (SKH), to sufficiently describe the latent space by the mixture of K-class hyperplanes. It can directly replace the conventional single K-class hyperplane optimization as the new paradigm for noise-robust representation learning. When collaborated with the popular ArcFace on million-level data representation learning, we found that the switchable manner in SKH can effectively eliminate the gradient conflict generated by real-world label noise on a single K-class hyperplane. Moreover, combined with the margin-based loss functions (e.g. ArcFace), we propose a simple Posterior Data Clean strategy to reduce the model optimization deviation on clean dataset caused by the reduction of valid categories in each K-class hyperplane. Extensive experiments demonstrate that the proposed SKH easily achieves new state-of-the-art on IJB-B and IJB-C by encouraging noise-robust representation learning. Our code will be available at https://github.com/liubx07/SKH.git.
BibTeX
@inproceedings{liu2021switchable,
  author = {Boxiao Liu and Guanglu Song and Manyuan Zhang and Haihang You and Yu Liu},
  title = {{Switchable K-class Hyperplanes for Noise-Robust Representation Learning}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2021},
  doi = {10.1109/iccv48922.2021.00301},
}

Loading related content...

Figure