Minimum Class Confusion for Versatile Domain Adaptation

There are a variety of DA scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi-target DA. It is notable that existing DA methods are generally designed only for a specific scenario, and may underperform for scenarios they are not tailored to. A versatile method, which can handle several different scenarios without any extra modifications, is still remained to be explored. Towards such purpose, a more general inductive bias other than the domain alignment should be explored. In this paper, we delve into a missing piece of existing methods: class confusion, the tendency that a classifier confuses the predictions between the correct and ambiguous classes for target examples, which exists in all of the scenarios above. We unveil that reducing such pair-wise class confusion brings about significant transfer gains. Based on this, we propose a general loss function: Minimum Class Confusion (MCC). It can be characterized by (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying fast convergence speed (about 3 times faster than mainstream adversarial methods); (2) a versatile approach that can handle the four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on the largest and hardest dataset to date (7.25% on DomainNet). Strong performance in the two scenarios proposed in this paper: Multi-Source Partial and Multi-Target Partial DA, further proves its versatility. In addition, it can also be used as a general regularizer that is orthogonal and complementary to a variety of existing DA methods, accelerating convergence and pushing those readily competitive methods to a stronger level.