NLNL: Negative Learning for Noisy Labels
This addresses the issue of degraded performance in image classification when labels are noisy, which is a common problem in real-world datasets, though it is an incremental improvement over existing noisy label methods.
The paper tackles the problem of training convolutional neural networks with noisy labels by introducing Negative Learning (NL), which uses complementary labels to reduce incorrect information, and extends it with Selective Negative and Positive Learning (SelNLPL) to improve convergence. The method achieves state-of-the-art accuracy for noisy data classification, demonstrating superior filtering of noisy data.
Convolutional Neural Networks (CNNs) provide excellent performance when used for image classification. The classical method of training CNNs is by labeling images in a supervised manner as in "input image belongs to this label" (Positive Learning; PL), which is a fast and accurate method if the labels are assigned correctly to all images. However, if inaccurate labels, or noisy labels, exist, training with PL will provide wrong information, thus severely degrading performance. To address this issue, we start with an indirect learning method called Negative Learning (NL), in which the CNNs are trained using a complementary label as in "input image does not belong to this complementary label." Because the chances of selecting a true label as a complementary label are low, NL decreases the risk of providing incorrect information. Furthermore, to improve convergence, we extend our method by adopting PL selectively, termed as Selective Negative Learning and Positive Learning (SelNLPL). PL is used selectively to train upon expected-to-be-clean data, whose choices become possible as NL progresses, thus resulting in superior performance of filtering out noisy data. With simple semi-supervised training technique, our method achieves state-of-the-art accuracy for noisy data classification, proving the superiority of SelNLPL's noisy data filtering ability.