Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation

By Hongbin Lin, Yifan Zhang, Zhen Qiu, Shuaicheng Niu, Chuang Gan, Yanxia Liu, Mingkui Tan. 2022

59 citations recorded by the source corpus.

This paper studies a new, practical but challenging problem, called Class-Incremental Unsupervised Domain Adaptation (CI-UDA), where the labeled source domain contains all classes, but the classes in the unlabeled target domain increase sequentially. This problem is challenging due to two difficulties. First, source and target label sets are inconsistent at each time step, which makes it difficult to conduct accurate domain alignment. Second, previous target classes are unavailable in the current step, resulting in the forgetting of previous knowledge. To address this problem, we propose a novel Prototype-guided Continual Adaptation (ProCA) method, consisting of two solution strategies. 1) Label prototype identification: we identify target label prototypes by detecting shared classes with cumulative prediction probabilities of target samples. 2) Prototype-based alignment and replay: based on the identified label prototypes, we align both domains and enforce the model to retain previous knowledge. With these two strategies, ProCA is able to adapt the source model to a class-incremental unlabeled target domain effectively. Extensive experiments demonstrate the effectiveness and superiority of ProCA in resolving CI-UDA. The source code is available at https://github.com/Hongbin98/ProCA.git

Subfields: Artificial Intelligence, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Meta & Continual Learning

Citations in the corpus

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “Besides, other practical challenges have been considered and incorporated, such as multiple labels [215], noisy labels [29], [216], hierarchical granularity [2] and sub-populations [254], mixture of task similarity [207], long-tailed distribution [267], domain alignment [256],”
Towards Stable Test-Time Adaptation in Dynamic Wild World (2023, background): “…mitigate distribution shifts, such as devising a domain discrimi-nator to align source and target domains at feature level (Pei et al., 2018; Saito et al., 2018; Zhang et al., 2020b;a) and aligning the prototypes of source and target domains through a contrastive learning manner (Lin et al., 2022).”