This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign clusters to unlabelled data. To avoid over-fitting the learnt embedding to labelled data, we take inspiration from self-supervised representation learning by noise-contrastive estimation and extend it to jointly handle labelled and unlabelled data. In particular, we propose using category discrimination on labelled data and cross-modal discrimination on multi-modal data to augment instance discrimination used in conventional contrastive learning approaches. We further employ Winner-Take-All (WTA) hashing algorithm on the shared representation space to generate pairwise pseudo labels for unlabelled data to better predict cluster assignments. We thoroughly evaluate our framework on large-scale multi-modal video benchmarks Kinetics-400 and VGG-Sound, and image benchmarks CIFAR10, CIFAR100 and ImageNet, obtaining state-of-the-art results.
翻译:本文研究与不同但相关类别标签的单一和多模式数据的新分类发现问题。我们提出了一个通用的、端对端框架,以共同学习可靠的表示方式,并分配无标签数据的组群。为了避免将所学到的嵌入的嵌入于标签数据中的时间过长,我们从自我监督的代号学习中汲取灵感,通过噪声调估测,将其扩大到联合处理贴标签和无标签数据。特别是,我们提议在多模式数据的标签数据和跨模式歧视上使用分类歧视,以扩大传统对比学习方法中使用的实例歧视。我们进一步在共享代号空间使用Winner-Joe-All(WTA)的算法,以生成无标签数据的双伪标签,以更好地预测群集任务。我们彻底评估了我们关于大规模多模式视频基准Kinetics-400和VGG-Sound的框架,以及图像基准CIFAR10、CIFAR100和图像网络,以获得最新结果。