LGCVMay 27, 2022

Dynamic Domain Generalization

arXiv:2205.13913v124 citationsh-index: 20Has Code
Originality Highly original
AI Analysis

This addresses the challenge of generalizing machine learning models to new, unseen domains without additional training, which is crucial for real-world applications but is incremental as it builds on existing domain generalization frameworks.

The paper tackles the problem of domain generalization by introducing Dynamic Domain Generalization (DDG), a method that adjusts model parameters without retraining to adapt to unseen target domains, achieving state-of-the-art results in experiments.

Domain generalization (DG) is a fundamental yet very challenging research topic in machine learning. The existing arts mainly focus on learning domain-invariant features with limited source domains in a static model. Unfortunately, there is a lack of training-free mechanism to adjust the model when generalized to the agnostic target domains. To tackle this problem, we develop a brand-new DG variant, namely Dynamic Domain Generalization (DDG), in which the model learns to twist the network parameters to adapt the data from different domains. Specifically, we leverage a meta-adjuster to twist the network parameters based on the static model with respect to different data from different domains. In this way, the static model is optimized to learn domain-shared features, while the meta-adjuster is designed to learn domain-specific features. To enable this process, DomainMix is exploited to simulate data from diverse domains during teaching the meta-adjuster to adapt to the upcoming agnostic target domains. This learning mechanism urges the model to generalize to different agnostic target domains via adjusting the model without training. Extensive experiments demonstrate the effectiveness of our proposed method. Code is available at: https://github.com/MetaVisionLab/DDG

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes