Contrastive learning (CL), a self-supervised learning approach, can effectively learn visual representations from unlabeled data. However, CL requires learning on vast quantities of diverse data to achieve good performance, without which the performance of CL will greatly degrade. To tackle this problem, we propose a framework with two approaches to improve the data efficiency of CL training by generating beneficial samples and joint learning. The first approach generates hard samples for the main model. The generator is jointly learned with the main model to dynamically customize hard samples based on the training state of the main model. With the progressively growing knowledge of the main model, the generated samples also become harder to constantly encourage the main model to learn better representations. Besides, a pair of data generators are proposed to generate similar but distinct samples as positive pairs. In joint learning, the hardness of a positive pair is progressively increased by decreasing their similarity. In this way, the main model learns to cluster hard positives by pulling the representations of similar yet distinct samples together, by which the representations of similar samples are well-clustered and better representations can be learned. Comprehensive experiments show superior accuracy and data efficiency of the proposed methods over the state-of-the-art on multiple datasets. For example, about 5% accuracy improvement on ImageNet-100 and CIFAR-10, and more than 6% accuracy improvement on CIFAR-100 are achieved for linear classification. Besides, up to 2x data efficiency for linear classification and up to 5x data efficiency for transfer learning are achieved.
翻译:自我监督的对比学习(CL)是一种自我监督的学习方法,它能够有效地从未贴标签的数据中学习视觉表现。然而,CL需要学习大量不同的数据,才能取得良好的表现,否则CL的性能将大大降低。为了解决这一问题,我们提出了一个框架,其中有两个方法可以提高CL培训的数据效率,方法是通过生成有益的样本和共同学习来提高CL培训的数据效率。第一种方法为主模型生成硬样本。发电机与主要模型的主要模型共同学习,根据主模型的培训状态动态定制硬样本。随着对主要模型的了解不断增长,生成的样本也越来越难不断鼓励主要模型学习更好的表现。此外,还提议用一对数据生成器生成类似但不同的样本,作为正对对配。在联合学习中,正对对配的硬性逐渐增加。以这种方式为主模型制作硬性样本,通过对类似但有区别的样本进行展示,通过对类似样本的描述得到很好的组合,并且可以更好地进行展示。 全面实验表明,在5-RFAR的分类中,在5级数据中实现了更高的准确性和数据改进的精确度和数据更新。