Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation

By Xu Yang, Cheng Deng, Tongliang Liu, Dacheng Tao. 2020

153 citations recorded by the source corpus.

Domain adaptation, which transfers the knowledge from label-rich source domain to unlabeled target domains, is a challenging task in machine learning. The prior domain adaptation methods focus on pairwise adaptation assumption with a single source and a single target domain, while little work concerns the scenario of one source domain and multiple target domains. Applying pairwise adaptation methods to this setting may be suboptimal, as they fail to consider the semantic association among multiple target domains. In this work we propose a deep semantic information propagation approach in the novel context of multiple unlabeled target domains and one labeled source domain. Our model aims to learn a unified subspace common for all domains with a heterogeneous graph attention network, where the transductive ability of the graph attention network can conduct semantic propagation of the related samples among multiple domains. In particular, the attention mechanism is applied to optimize the relationships of multiple domain samples for better semantic transfer. Then, the pseudo labels of the target domains predicted by the graph attention network are utilized to learn domain-invariant representations by aligning labeled source centroid and pseudo-labeled target centroid. We test our approach on four challenging public datasets, and it outperforms several popular domain adaptation methods.

Subfields: Artificial Intelligence, 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. Yanan Gu
2. Cheng Deng
3. Kun-Juan Wei
4. Xu Yang

In Computer Vision and Pattern Recognition

1. Yanan Gu
2. Kun-Juan Wei
3. Cheng Deng
4. Xu Yang
5. Dacheng Tao

Citations in the corpus

• Class-Incremental Instance Segmentation via Multi-Teacher Networks (2021, background): “Due to the development of deep learning, like other visual tasks (Yang et al. 2018, 2020a; Dang et al. 2020; Yang et al. 2020b; Deng et al. 2019), instance segmentation meth-ods have achieved amazing results.”
• Dual Contrastive Prediction for Incomplete Multi-View Representation Learning (2022, unknown): “like clustering [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], classification [14], [15], [16], [17], and human action recognition [18].”
• Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency (2022, background): “Intelligent systems [24, 30, 33, 49, 53, 56] based on convolutional neural networks have achieved excellent performance on various tasks, some of which even exceed humanlevel performance.”