Multi-scale Feature Alignment for Continual Learning of Unlabeled Domains
Methods for unsupervised domain adaptation (UDA) help to improve the performance of deep neural networks on unseen domains without any labeled data. Especially in medical disciplines such as histopathology, this is crucial since large datasets with detailed annotations are scarce. While the majority of existing UDA methods focus on the adaptation from a labeled source to a single unlabeled target domain, many real-world applications with a long life cycle involve more than one target domain. Thus, the ability to sequentially adapt to multiple target domains becomes essential. In settings where the data from previously seen domains cannot be stored, e.g., due to data protection regulations, the above becomes a challenging continual learning problem. To this end, we propose to use generative feature-driven image replay in conjunction with a dual-purpose discriminator that not only enables the generation of images with realistic features for replay, but also promotes feature alignment during domain adaptation. We evaluate our approach extensively on a sequence of three histopathological datasets for tissue-type classification, achieving state-of-the-art results. We present detailed ablation experiments studying our proposed method components and demonstrate a possible use-case of our continual UDA method for an unsupervised patch-based segmentation task given high-resolution tissue images.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningDomain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery
Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamical…
Novel Class DiscoveryAnnotation-Free Class-Incremental Learning
Despite significant progress in continual learning ranging from architectural novelty to clever strategies for mitigating catastrophic forgetting most existing methods rest on a strong but unrealistic assumption the avai…
class-incremental learningContinual LearningScalable Adversarial Online Continual Learning
Adversarial continual learning is effective for continual learning problems because of the presence of feature alignment process generating task-invariant features having low susceptibility to the catastrophic forgetting…
Continual LearningMeta-LearningUnsupervised Continual Domain Shift Learning with Multi-Prototype Modeling
In real-world applications, deep neural networks may encounter constantly changing environments, where the test data originates from continually shifting unlabeled target domains. This problem, known as Unsupervised …
Unsupervised Continual Domain Shift LearningDivide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning
Semi-supervised continual learning (SSCL) seeks to leverage both labeled and unlabeled data in a sequential learning setup, aiming to reduce annotation costs while managing continual data arrival. SSCL introduces complex…
Continual Learning