Learning to Discover Novel Visual Categories via Deep Transfer Clustering
This work addresses the challenge of novel category discovery in computer vision, which is incremental as it builds on existing clustering and transfer learning methods.
The paper tackles the problem of discovering novel object categories in unlabeled image collections by leveraging prior knowledge of related classes to reduce clustering ambiguity and improve class discovery quality. It introduces a transfer learning extension of Deep Embedded Clustering with improvements like a representation bottleneck and temporal ensembling, along with a method to estimate the number of classes, achieving substantial outperformance over state-of-the-art techniques on benchmarks such as ImageNet and CIFAR-100.
We consider the problem of discovering novel object categories in an image collection. While these images are unlabelled, we also assume prior knowledge of related but different image classes. We use such prior knowledge to reduce the ambiguity of clustering, and improve the quality of the newly discovered classes. Our contributions are twofold. The first contribution is to extend Deep Embedded Clustering to a transfer learning setting; we also improve the algorithm by introducing a representation bottleneck, temporal ensembling, and consistency. The second contribution is a method to estimate the number of classes in the unlabelled data. This also transfers knowledge from the known classes, using them as probes to diagnose different choices for the number of classes in the unlabelled subset. We thoroughly evaluate our method, substantially outperforming state-of-the-art techniques in a large number of benchmarks, including ImageNet, OmniGlot, CIFAR-100, CIFAR-10, and SVHN.