使用协同样本选择和对比半监督学习进行含噪标签学习
Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning
AI总结：
针对含噪标签学习中干净集混入噪声样本导致确认偏差的问题，提出利用预训练模型CLIP的协同样本选择方法，并结合对比半监督学习联合训练CLIP提示与DNN分类器，有效消除噪声样本并提升泛化性能。
摘要：
含噪标签学习（LNL）已被广泛研究，现有方法通常遵循在干净样本选择和半监督学习（SSL）之间交替进行的框架。然而，该方法存在一个局限：通过自训练训练的深度神经网络（DNN）分类器所选出的干净集不可避免地包含噪声样本。这种干净样本与噪声样本的混合会在SSL期间误导DNN训练，由于样本选择中的误差累积导致确认偏差，从而损害泛化性能。为解决此问题，我们提出了一种名为协同样本选择（CSS）的方法，该方法利用了大规模预训练模型CLIP。CSS旨在从已识别的干净集中移除混合的噪声样本。我们通过训练一个二维高斯混合模型（2D-GMM）来实现这一点，该模型将CLIP的概率与DNN分类器的预测相结合。为了进一步增强CLIP对LNL的适应性，我们在半监督学习中引入了带有对比损失的协同训练机制。这使我们能够联合训练CLIP的提示和DNN分类器，从而改善特征表示，提升DNN的分类性能，并对我们的协同样本选择产生互惠益处。通过结合CLIP的辅助信息并利用提示微调，我们有效地消除了干净集中的噪声样本，并减轻了训练期间的确认偏差。在多个基准数据集上的实验结果证明了我们提出的方法与最先进方法相比的有效性。
英文摘要：
Learning with noisy labels (LNL) has been extensively studied, with existing approaches typically following a framework that alternates between clean sample selection and semi-supervised learning (SSL). However, this approach has a limitation: the clean set selected by the Deep Neural Network (DNN) classifier, trained through self-training, inevitably contains noisy samples. This mixture of clean and noisy samples leads to misguidance in DNN training during SSL, resulting in impaired generalization performance due to confirmation bias caused by error accumulation in sample selection. To address this issue, we propose a method called Collaborative Sample Selection (CSS), which leverages the large-scale pre-trained model CLIP. CSS aims to remove the mixed noisy samples from the identified clean set. We achieve this by training a 2-Dimensional Gaussian Mixture Model (2D-GMM) that combines the probabilities from CLIP with the predictions from the DNN classifier. To further enhance the adaptation of CLIP to LNL, we introduce a co-training mechanism with a contrastive loss in semi-supervised learning. This allows us to jointly train the prompt of CLIP and the DNN classifier, resulting in improved feature representation, boosted classification performance of DNNs, and reciprocal benefits to our Collaborative Sample Selection. By incorporating auxiliary information from CLIP and utilizing prompt fine-tuning, we effectively eliminate noisy samples from the clean set and mitigate confirmation bias during training. Experimental results on multiple benchmark datasets demonstrate the effectiveness of our proposed method in comparison with the state-of-the-art approaches.
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。
