利用带噪声网络数据的抗噪混合原型学习
Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Data
AI总结：
针对少量干净标注与大量带噪网络图像的分类问题，提出 SimNoiPro 相似度最大化损失，构建抗噪混合原型并端到端建模图像关系，在两个扩展小样本基准上优于已有方法。
摘要：
我们关注一个具有挑战性的问题：在仅给定少量干净标注图像的情况下，从大量可能相关但标签带噪的网络图像中学习一个无偏分类器。该问题具有很强的现实意义，因为它通过利用可免费获取且带有噪声标签的网络图像来降低昂贵的标注成本。通常，原型是用于分类或识别其他图像的代表性图像或特征。然而，在少量干净样本与大量噪声样本并存的场景中，由于不相关噪声图像的存在，类别原型可能会出现严重偏差。由此产生的原型紧凑性和判别性较差，因为以往方法没有考虑带噪网络图像集合中图像的多样性。另一方面，用于类别原型生成的噪声图像与干净图像之间的关系建模并未以端到端方式学习，从而导致类别原型并非最优。本文提出一种名为 SimNoiPro 的相似度最大化损失。我们的 SimNoiPro 首先生成由干净原型和抗噪原型组成的抗噪混合原型，随后将这些原型彼此拉近。该方法通过显式划分来考虑噪声图像的多样性，并克服优化不一致问题。这使得干净图像与噪声图像之间能够实现更好的关系建模，并有助于从噪声图像集中提取合理而有用的信息。在两个扩展的小样本分类基准上的评估结果证实，我们的 SimNoiPro 在衡量图像关系和清理噪声数据方面优于以往方法。
英文摘要：
We focus on the challenging problem of learning an unbiased classifier from a large number of potentially relevant but noisily labeled web images given only a few clean labeled images. This problem is particularly practical because it reduces the expensive annotation costs by utilizing freely accessible web images with noisy labels. Typically, prototypes are representative images or features used to classify or identify other images. However, in the few clean and many noisy scenarios, the class prototype can be severely biased due to the presence of irrelevant noisy images. The resulting prototypes are less compact and discriminative, as previous methods do not take into account the diverse range of images in the noisy web image collections. On the other hand, the relation modeling between noisy and clean images is not learned for the class prototype generation in an end-to-end manner, which results in a suboptimal class prototype. In this article, we introduce a similarity maximization loss named SimNoiPro. Our SimNoiPro first generates noise-tolerant hybrid prototypes composed of clean and noise-tolerant prototypes and then pulls them closer to each other. Our approach considers the diversity of noisy images by explicit division and overcomes the optimization discrepancy issue. This enables better relation modeling between clean and noisy images and helps extract judicious information from the noisy image set. The evaluation results on two extended few-shot classification benchmarks confirm that our SimNoiPro outperforms prior methods in measuring image relations and cleaning noisy data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
