Learning from Noisy Data with Robust Representation Learning

Junnan Li, Caiming Xiong, Steven Hoi

Abstract

Learning from noisy data has attracted much attention, where most methods focus on label noise. In this work, we propose a new framework which simultaneously addresses three types of noise commonly seen in real-world data: label noise, out-of-distribution input, and input corruption. In contrast to most existing methods, we combat noise by learning robust representation. Specifically, we embed images into a low-dimensional subspace by training an autoencoder on the deep features. We regularize the geometric structure of the subspace with robust contrastive learning, which includes an unsupervised consistency loss and a supervised mixup prototypical loss. Furthermore, we leverage the structure of the learned subspace for noise cleaning, by aggregating information from neighboring samples. Experiments on multiple benchmarks demonstrate state-of-the-art performance of our method and robustness of the learned representation. Our code will be released.
BibTeX
@inproceedings{li2021learning,
  author = {Junnan Li and Caiming Xiong and Steven Hoi},
  title = {{Learning from Noisy Data with Robust Representation Learning}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {2021},
  url = {https://openreview.net/forum?id=CjE-vbvtzJZ},
}

Loading related content...

Figure