English

Attention-Aware Noisy Label Learning for Image Classification

Computer Vision and Pattern Recognition 2020-10-01 v1

Abstract

Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision, such as image/video classification. The cheapest way to obtain a large body of labeled visual data is to crawl from websites with user-supplied labels, such as Flickr. However, these samples often tend to contain incorrect labels (i.e. noisy labels), which will significantly degrade the network performance. In this paper, the attention-aware noisy label learning approach (A2NLA^2NL) is proposed to improve the discriminative capability of the network trained on datasets with potential label noise. Specifically, a Noise-Attention model, which contains multiple noise-specific units, is designed to better capture noisy information. Each unit is expected to learn a specific noisy distribution for a subset of images so that different disturbances are more precisely modeled. Furthermore, a recursive learning process is introduced to strengthen the learning ability of the attention network by taking advantage of the learned high-level knowledge. To fully evaluate the proposed method, we conduct experiments from two aspects: manually flipped label noise on large-scale image classification datasets, including CIFAR-10, SVHN; and real-world label noise on an online crawled clothing dataset with multiple attributes. The superior results over state-of-the-art methods validate the effectiveness of our proposed approach.

Keywords

Cite

@article{arxiv.2009.14757,
  title  = {Attention-Aware Noisy Label Learning for Image Classification},
  author = {Zhenzhen Wang and Chunyan Xu and Yap-Peng Tan and Junsong Yuan},
  journal= {arXiv preprint arXiv:2009.14757},
  year   = {2020}
}

Comments

10 pages, 8 figures

R2 v1 2026-06-23T18:54:49.965Z