Learning to Generalize across Domains on Single Test Samples

by   Zehao Xiao, et al.

We strive to learn a model from a set of source domains that generalizes well to unseen target domains. The main challenge in such a domain generalization scenario is the unavailability of any target domain data during training, resulting in the learned model not being explicitly adapted to the unseen target domains. We propose learning to generalize across domains on single test samples. We leverage a meta-learning paradigm to learn our model to acquire the ability of adaptation with single samples at training time so as to further adapt itself to each single test sample at test time. We formulate the adaptation to the single test sample as a variational Bayesian inference problem, which incorporates the test sample as a conditional into the generation of model parameters. The adaptation to each test sample requires only one feed-forward computation at test time without any fine-tuning or self-supervised training on additional data from the unseen domains. Extensive ablation studies demonstrate that our model learns the ability to adapt models to each single sample by mimicking domain shifts during training. Further, our model achieves at least comparable – and often better – performance than state-of-the-art methods on multiple benchmarks for domain generalization.


MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption

An unresolved problem in Deep Learning is the ability of neural networks...

Energy-Based Test Sample Adaptation for Domain Generalization

In this paper, we propose energy-based sample adaptation at test time fo...

Learning Variational Neighbor Labels for Test-Time Domain Generalization

This paper strives for domain generalization, where models are trained e...

Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning

Learning-based image dehazing methods are essential to assist autonomous...

Self-Supervision Meta-Learning for One-Shot Unsupervised Cross-Domain Detection

Deep detection models have largely demonstrated to be extremely powerful...

Semantic Self-adaptation: Enhancing Generalization with a Single Sample

Despite years of research, out-of-domain generalization remains a critic...

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

Fully test-time adaptation aims to adapt the network model based on sequ...

Please sign up or login with your details

Forgot password? Click here to reset