Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation. (arXiv:2107.03358v2 [cs.CV] UPDATED)

In this paper, we tackle the problem of novel visual category discovery,
i.e., grouping unlabelled images from new classes into different semantic
partitions by leveraging a labelled dataset that contains images from other
different but relevant categories. This is a more realistic and challenging
setting than conventional semi-supervised learning. We propose a two-branch
learning framework for this problem, with one branch focusing on local
part-level information and the other branch focusing on overall
characteristics. To transfer knowledge from the labelled …

arxiv cv discovery statistics