Prior Knowledge Guided Unsupervised Domain Adaptation

by   Tao Sun, et al.

The waive of labels in the target domain makes Unsupervised Domain Adaptation (UDA) an attractive technique in many real-world applications, though it also brings great challenges as model adaptation becomes harder without labeled target data. In this paper, we address this issue by seeking compensation from target domain prior knowledge, which is often (partially) available in practice, e.g., from human expertise. This leads to a novel yet practical setting where in addition to the training data, some prior knowledge about the target class distribution are available. We term the setting as Knowledge-guided Unsupervised Domain Adaptation (KUDA). In particular, we consider two specific types of prior knowledge about the class distribution in the target domain: Unary Bound that describes the lower and upper bounds of individual class probabilities, and Binary Relationship that describes the relations between two class probabilities. We propose a general rectification module that uses such prior knowledge to refine model generated pseudo labels. The module is formulated as a Zero-One Programming problem derived from the prior knowledge and a smooth regularizer. It can be easily plugged into self-training based UDA methods, and we combine it with two state-of-the-art methods, SHOT and DINE. Empirical results on four benchmarks confirm that the rectification module clearly improves the quality of pseudo labels, which in turn benefits the self-training stage. With the guidance from prior knowledge, the performances of both methods are substantially boosted. We expect our work to inspire further investigations in integrating prior knowledge in UDA. Code is available at


page 1

page 2

page 3

page 4


BUDA: Boundless Unsupervised Domain Adaptation in Semantic Segmentation

In this work, we define and address "Boundless Unsupervised Domain Adapt...

Unsupervised Domain Adaptation for Anatomical Landmark Detection

Recently, anatomical landmark detection has achieved great progresses on...

Energy-constrained Self-training for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a...

Online Learning and Planning in Partially Observable Domains without Prior Knowledge

How an agent can act optimally in stochastic, partially observable domai...

SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation

As acquiring manual labels on data could be costly, unsupervised domain ...

FeatFSDA: Towards Few-shot Domain Adaptation for Video-based Activity Recognition

Domain adaptation is essential for activity recognition, as common spati...

Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions

Accelerating the discovery of novel and more effective therapeutics is a...

Please sign up or login with your details

Forgot password? Click here to reset