Domain-Aware Augmentations for Unsupervised Online General Continual Learning
Continual Learning has been challenging, especially when dealing with unsupervised scenarios such as Unsupervised Online General Continual Learning (UOGCL), where the learning agent has no prior knowledge of class boundaries or task change information. While previous research has focused on reducing forgetting in supervised setups, recent studies have shown that self-supervised learners are more resilient to forgetting. This paper proposes a novel approach that enhances memory usage for contrastive learning in UOGCL by defining and using stream-dependent data augmentations together with some implementation tricks. Our proposed method is simple yet effective, achieves state-of-the-art results compared to other unsupervised approaches in all considered setups, and reduces the gap between supervised and unsupervised continual learning. Our domain-aware augmentation procedure can be adapted to other replay-based methods, making it a promising strategy for continual learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningContrastive LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Augmentation-based Domain Generalization for Semantic Segmentation
Unsupervised Domain Adaptation (UDA) and domain generalization (DG) are two research areas that aim to tackle the lack of generalization of Deep Neural Networks (DNNs) towards unseen domains. While UDA methods have acces…
Domain AdaptationDomain GeneralizationSemantic SegmentationUnsupervised Domain AdaptationAugmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices
Unsupervised graph representation learning is critical to a wide range of applications where labels may be scarce or expensive to procure. Contrastive learning (CL) is an increasingly popular paradigm for such settings a…
ClassificationContrastive LearningData AugmentationDocument Classification+5AugCSE: Contrastive Sentence Embedding with Diverse Augmentations
Data augmentation techniques have been proven useful in many applications in NLP fields. Most augmentations are task-specific, and cannot be used as a general-purpose tool. In our work, we present AugCSE, a unified frame…
Data AugmentationDomain AdaptationSemantic Textual SimilaritySentence+2Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations without labeled data. Most SSL approaches rely on strong, well-established, handcrafted data augmentations to generate divers…
Self-Supervised LearningRepresentation LearningUnsupervised Domain Adaptation for Action Recognition via Self-Ensembling and Conditional Embedding Alignment
Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions, but adoption remains limited due to the lack of expert annotations and …
Action RecognitionData AugmentationDomain AdaptationPseudo Label+2