Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment

By Alex Gabourie, Mohammad Rostami, Phillip E. Pope, Soheil Kolouri, Kyungnam Kim. 2019

24 citations recorded by the source corpus.

We address the problem of unsupervised domain adaptation (UDA) by learning a cross-domain agnostic embedding space, where the distance between the probability distributions of the two source and target visual domains is minimized. We use the output space of a shared cross-domain deep encoder to model the embedding space and use the Sliced-Wasserstein Distance (SWD) to measure and minimize the distance between the embedded distributions of two source and target domains to enforce the embedding to be domain-agnostic. Additionally, we use the source domain labeled data to train a deep classifier from the embedding space to the label space to enforce the embedding space to be discriminative. As a result of this training scheme, we provide an effective solution to train the deep classification network on the source domain such that it will generalize well on the target domain, where only unlabeled training data is accessible. To mitigate the challenge of class matching, we also align corresponding classes in the embedding space by using high confidence pseudo-labels for the target domain, i.e. assigning the class for which the source classifier has a high prediction probability. We provide experimental results on UDA benchmark tasks to demonstrate that our method is effective and leads to state-of-the-art performance.

Subfields: Artificial Intelligence, Cancer Research, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Serban Stan
2. Aram Galstyan
3. Mohammad Rostami
4. Fei Ye
5. Adrian G. Bors

In Cancer Research

1. Aram Galstyan
2. Mohammad Rostami
3. Serban Stan

In Computer Vision and Pattern Recognition

1. Serban Stan
2. Aram Galstyan
3. Mohammad Rostami

Citations in the corpus

• Unsupervised Model Adaptation for Continual Semantic Segmentation (2020, background): “A second class of UDA algorithms directly minimize suitable loss functions that enforce domain alignment (Wu et al. 2018; Zhang, David, and Gong 2017; Gabourie et al. 2019; Zhang et al. 2019; Lee et al. 2019; Yang and Soatto 2020).”
• Sequential Unsupervised Domain Adaptation through Prototypical Distributions (2020, methodology): “We have also included methods based on direct distribution matching that are more similar to our approach: DAN [10], DRCN [31], RevGrad [11], CAN [13], JAN [12], DACAD [32], and JDDA [33].”