MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation
arXiv:2103.13575
Abstract
For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics. However, the optimization objective of such domain alignment is generally not coordinated with that of the object classification task itself such that their descent directions for optimization may be inconsistent. This will reduce the effectiveness of domain alignment in improving the performance of UDA. In this paper, we aim to study and alleviate the optimization inconsistency problem between the domain alignment and classification tasks. We address this by proposing an effective meta-optimization based strategy dubbed MetaAlign, where we treat the domain alignment objective and the classification objective as the meta-train and meta-test tasks in a meta-learning scheme. MetaAlign encourages both tasks to be optimized in a coordinated way, which maximizes the inner product of the gradients of the two tasks during training. Experimental results demonstrate the effectiveness of our proposed method on top of various alignment-based baseline approaches, for tasks of object classification and object detection. MetaAlign helps achieve the state-of-the-art performance.
Accepted by CVPR2021
References in corpus (6)
- Learning Transferable Features with Deep Adaptation Networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- Theoretical Models of Learning to Learn
- Domain Generalization via Invariant Feature Representation
- Domain Generalization via Model-Agnostic Learning of Semantic Features
- Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector