Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay

Abstract

Learning in non-stationary environments is one of the biggest challenges in machine learning. Non-stationarity can be caused by either task drift, i.e., the drift in the conditional distribution of labels given the input data, or the domain drift, i.e., the drift in the marginal distribution of the input data. This paper aims to tackle this challenge in the context of continuous domain adaptation, where the model is required to learn new tasks adapted to new domains in a non-stationary environment while maintaining previously learned knowledge. To deal with both drifts, we propose variational domain-agnostic feature replay, an approach that is composed of three components: an inference module that filters the input data into domain-agnostic representations, a generative module that facilitates knowledge transfer, and a solver module that applies the filtered and transferable knowledge to solve the queries. We address the two fundamental scenarios in continuous domain adaptation, demonstrating the effectiveness of our proposed approach for practical usage.

References in corpus (10)

• Overcoming catastrophic forgetting in neural networks
• Learning Transferable Features with Deep Adaptation Networks
• Conditional Adversarial Domain Adaptation
• Continual Learning Through Synaptic Intelligence
• Progress & Compress: A scalable framework for continual learning
• Bridging Theory and Algorithm for Domain Adaptation
• Domain Agnostic Learning with Disentangled Representations
• Learning Disentangled Semantic Representation for Domain Adaptation
• DIVA: Domain Invariant Variational Autoencoders
• Improving Unsupervised Domain Adaptation with Variational Information Bottleneck

Cited by in corpus (8)

• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• Replay in Deep Learning: Current Approaches and Missing Biological Elements
• ODIN: Automated Drift Detection and Recovery in Video Analytics
• Gradient Regularized Contrastive Learning for Continual Domain Adaptation
• Delving into the Continuous Domain Adaptation
• Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time
• Learn Faster and Forget Slower via Fast and Stable Task Adaptation
• Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition