Convolutional neural networks (CNNs) have achieved significant success in image classification by utilizing large-scale datasets. However, it is still of great challenge to learn from scratch on small-scale datasets efficiently and effectively. With limited training datasets, the concepts of categories will be ambiguous since the over-parameterized CNNs tend to simply memorize the dataset, leading to poor generalization capacity. Therefore, it is crucial to study how to learn more discriminative representations while avoiding over-fitting. Since the concepts of categories tend to be ambiguous, it is important to catch more individual-wise information. Thus, we propose a new framework, termed Attract-and-Repulse, which consists of Contrastive Regularization (CR) to enrich the feature representations, Symmetric Cross Entropy (SCE) to balance the fitting for different classes and Mean Teacher to calibrate label information. Specifically, SCE and CR learn discriminative representations while alleviating over-fitting by the adaptive trade-off between the information of classes (attract) and instances (repulse). After that, Mean Teacher is used to further improve the performance via calibrating more accurate soft pseudo labels. Sufficient experiments validate the effectiveness of the Attract-and-Repulse framework. Together with other strategies, such as aggressive data augmentation, TenCrop inference, and models ensembling, we achieve the second place in ICCV 2021 VIPriors Image Classification Challenge.
翻译:通过使用大型数据集,在图像分类方面取得了显著的成功。然而,在小规模数据集上,从零开始以高效和有效的方式从零中学习,仍是一项艰巨的挑战。由于培训数据集有限,类别概念将模糊不清,因为过度隔离的CNN往往只是将数据集混为一模一样,导致笼统化能力差。因此,研究如何学习更具有歧视性的表述,同时避免过度适应,至关重要。由于类别概念往往模糊不清,因此必须掌握更多的个人信息。因此,我们提出一个新的框架,称为“吸引和重复”,由对比性正规化(CRR)组成,以丰富特征表达、对称跨环(SCECE)以平衡不同类别和对标签信息进行校准的教师。具体地说,SCE和CBC学习歧视性表述,同时通过适应性交易的类别信息(TRA)和实例(Repulate-Republess)之间的取配对。在此之后,BADS-Recretainality Forization Fority Forizations, 也用于通过更精确地校准的软性标签来进一步改进。