Generative appearance replay for continual unsupervised domain adaptation
Authors:
Preprint
Abstract
Deep learning models can achieve high accuracy when trained on large amounts of labeled data. However, real-world scenarios often involve several challenges: Training data may become available in installments, may originate from multiple different domains, and may not contain labels for training. Certain settings, for instance medical applications, often involve further restrictions that prohibit retention of previously seen data due to privacy regulations. In this work, to address such challenges, we study unsupervised segmentation in continual learning scenarios that involve domain shift. To that end, we introduce GarDA (Generative Appearance Replay for continual Domain Adaptation), a generative-replay based approach that can adapt a segmentation model sequentially to new domains with unlabeled data. In contrast to single-step unsupervised domain adaptation (UDA), continual adaptation to a sequence of domains enables leveraging and consolidation of information from multiple domains. Unlike previous approaches in incremental UDA, our method does not require access to previously seen data, making it applicable in many practical scenarios. We evaluate GarDA on two datasets with different organs and modalities, where it substantially outperforms existing techniques.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Generative feature-driven image replay for continual learningImage and Vision Computing, 2024
- Three types of incremental learningNature Machine Intelligence, 2022
- Continual Domain Incremental Learning for Chest X-Ray Classification in Low-Resource Clinical Settings2021
- Deep learning in histopathology: the path to the clinicNature Medicine, 2021
- REFUGE Challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographsMedical Image Analysis, 2020
- Continual lifelong learning with neural networks: A reviewNeural Networks, 2019
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: A reviewComputerized Medical Imaging and Graphics, 2013
- Optic disk feature extraction via modified deformable model technique for glaucoma analysisPattern Recognition, 2007
- Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem1989