Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation

Vision systems trained in closed-world scenarios fail when presented with new environmental conditions, new data distributions, and novel classes at deployment time. How to move towards open-world learning is a long-standing research question. The existing solutions mainly focus on specific aspects of the problem (single domain Open-Set, multi-domain Closed-Set), or propose complex strategies which combine several losses and manually tuned hyperparameters. In this work, we tackle multi-source Open-Set domain adaptation by introducing HyMOS: a straightforward model that exploits the power of contrastive learning and the properties of its hyperspherical feature space to correctly predict known labels on the target, while rejecting samples belonging to any unknown class. HyMOS includes style transfer among the instance transformations of contrastive learning to get domain invariance while avoiding the risk of negative-transfer. It also integrates a tailored data balancing to enforce cross-source alignment and exploits a carefully designed self-training strategy to extend this alignment to the target. A self-paced threshold is defined on the basis of the observed data distribution and updates online during training, allowing to handle the known-unknown separation. All these contributions provide a robust feature space with domain-aligned, compact, and well-separated class clusters where the classification can be performed on the basis of sample distances. We validate our method over three challenging datasets. The obtained results show that HyMOS outperforms several Open-Set and universal domain adaptation approaches, defining the new state-of-the-art.