Abstract
Self-supervised clustering methods have achieved increasing accuracy in recent years but do not yet perform as well as supervised classification methods. This contrasts with the situation for feature learning, where self-supervised features have recently surpassed the performance of supervised features on several important tasks. We hypothesize that the performance gap is due to the difficulty of specifying, without supervision, which features correspond to class differences that are semantic to humans. To reduce the performance gap, we introduce the "single-noun" prior - which states that semantic clusters tend to correspond to concepts that humans label by a single-noun. By utilizing a pre-trained network that maps images and sentences into a common space, we impose this prior obtaining a constrained optimization task. We show that our formulation is a special case of the facility location problem, and introduce a simple-yet-effective approach for solving this optimization task at scale. We test our approach on several commonly reported image clustering datasets and obtain significant accuracy gains over the best existing approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2104.03952
