Class Anchor Clustering

Dimity Miller, Niko Sünderhauf, Michael Milford, Feras Dayoub

Published: 01 Jan 2021, Last Modified: 28 Jan 2026Proceedings of the 2021 Winter Conference on Applications of Computer Vision (WACV '21)EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: In open set recognition, deep neural networks encounter object classes that were unknown during training. Existing open set classifiers distinguish between known and unknown classes by measuring distance in a network's logit space, assuming that known classes cluster closer to the training data than unknown classes. However, this approach is applied post-hoc to networks trained with cross-entropy loss, which does not guarantee this clustering behaviour. To overcome this limitation, we introduce the Class Anchor Clustering (CAC) loss. CAC is a distance-based loss that explicitly trains known classes to form tight clusters around anchored class-dependent centres in the logit space. We show that training with CAC achieves state-of-the-art performance for distance-based open set classifiers on all six standard benchmark datasets, with a 15.2% AUROC increase on the challenging TinyImageNet, without sacrificing classification accuracy. We also show that our anchored class centres achieve higher open set performance than learnt class centres, particularly on object-based datasets and large numbers of training classes.