ExpertNet: Adversarial Learning and Recovery Against Noisy Labels
This addresses the challenge of noisy labels in real-world datasets like social media images, offering a method to improve classification accuracy without requiring true labels, though it appears incremental as it builds on existing adversarial learning approaches.
The paper tackles the problem of noisy labels in datasets by proposing ExpertNet, a framework that uses both images and their noisy labels as learning features, achieving robust classification across various noise ratios and with only 20-50% of training data compared to state-of-the-art models.
Today's available datasets in the wild, e.g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i.e. erroneous, labels. Recent studies improve the robustness of deep models against noisy labels without the knowledge of true labels. In this paper, we advocate to derive a stronger classifier which proactively makes use of the noisy labels in addition to the original images - turning noisy labels into learning features. To such an end, we propose a novel framework, ExpertNet, composed of Amateur and Expert, which iteratively learn from each other. Amateur is a regular image classifier trained by the feedback of Expert, which imitates how human experts would correct the predicted labels from Amateur using the noise pattern learnt from the knowledge of both the noisy and ground truth labels. The trained Amateur and Expert proactively leverage the images and their noisy labels to infer image classes. Our empirical evaluations on noisy versions of CIFAR-10, CIFAR-100 and real-world data of Clothing1M show that the proposed model can achieve robust classification against a wide range of noise ratios and with as little as 20-50% training data, compared to state-of-the-art deep models that solely focus on distilling the impact of noisy labels.