Training a deep neural network heavily relies on a large amount of training data with accurate annotations. To alleviate this problem, various methods have been proposed to annotate the data automatically. However, automatically generating annotations will inevitably yields noisy labels. In this paper, we propose a Data Selection and joint Training (DST) method to automatically select training samples with accurate annotations. Specifically, DST fits a mixture model according to the original annotation as well as the predicted label for each training sample, and the mixture model is utilized to dynamically divide the training dataset into a correctly labeled dataset, a correctly predicted set and a wrong dataset. Then, DST is trained with these datasets in a supervised manner. Due to confirmation bias problem, we train the two networks alternately, and each network is tasked to establish the data division to teach another network. For each iteration, the correctly labeled and predicted labels are reweighted respectively by the probabilities from the mixture model, and a uniform distribution is used to generate the probabilities of the wrong samples. Experiments on CIFAR-10, CIFAR-100 and Clothing1M demonstrate that DST is the comparable or superior to the state-of-the-art methods.
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Jo-SRC: A Contrastive Approach for Combating Noisy Labels
Nanjing University of Science and Technology（南京理工大学）；University of Electronic Science and Technology of China（电子科技大学）；The University of Adelaide（阿德莱德大学）；University of Technology Sydney（悉尼科技大学）
由于深度神经网络（DNN）中的记忆效应，使用噪声标签进行训练通常会导致模型性能较差。现有的最先进的方法主要采用样本选择策略，其选择小损失样本用于后续训练。然而，现有文献倾向于在每个小批次内进行样本选择，忽略了不同小批次中噪声比的不平衡。此外，高损失样本中的宝贵知识被浪费了。为此，我们提出了一种抗噪声的方法Jo-SRC（Joint Sample Selection and Model Regularization based on Consistency）。具体来说，我们以对比学习的方式训练网络。从两个不同的角度对每个样本进行预测，以估计其干净或分布外的“可能性”。此外，我们提出了一个联合损失，以提高模型的推广性能，通过引入一致性正则化。大量的实验已经验证了我们的方法优于现有的国家的最先进的方法。
Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
Xi’an Jiaotong University（西安交通大学）；Hong Kong Polytechnic University（香港理工大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；The Macau University of Science and Technology（澳门科技大学）
