{
  "id": "2104.06574",
  "version": "v1",
  "published": "2021-04-14T01:32:25.000Z",
  "updated": "2021-04-14T01:32:25.000Z",
  "title": "Joint Negative and Positive Learning for Noisy Labels",
  "authors": [
    "Youngdong Kim",
    "Juseung Yun",
    "Hyounguk Shon",
    "Junmo Kim"
  ],
  "comment": "CVPR 2021, Accepted",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Training of Convolutional Neural Networks (CNNs) with data with noisy labels is known to be a challenge. Based on the fact that directly providing the label to the data (Positive Learning; PL) has a risk of allowing CNNs to memorize the contaminated labels for the case of noisy data, the indirect learning approach that uses complementary labels (Negative Learning for Noisy Labels; NLNL) has proven to be highly effective in preventing overfitting to noisy data as it reduces the risk of providing faulty target. NLNL further employs a three-stage pipeline to improve convergence. As a result, filtering noisy data through the NLNL pipeline is cumbersome, increasing the training cost. In this study, we propose a novel improvement of NLNL, named Joint Negative and Positive Learning (JNPL), that unifies the filtering pipeline into a single stage. JNPL trains CNN via two losses, NL+ and PL+, which are improved upon NL and PL loss functions, respectively. We analyze the fundamental issue of NL loss function and develop new NL+ loss function producing gradient that enhances the convergence of noisy data. Furthermore, PL+ loss function is designed to enable faster convergence to expected-to-be-clean data. We show that the NL+ and PL+ train CNN simultaneously, significantly simplifying the pipeline, allowing greater ease of practical use compared to NLNL. With a simple semi-supervised training technique, our method achieves state-of-the-art accuracy for noisy data classification based on the superior filtering ability.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-04-14T01:32:25.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "noisy labels",
      "positive learning",
      "joint negative",
      "method achieves state-of-the-art accuracy",
      "loss function producing gradient"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}