Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach
By Behnam Gholami, Pritish Sahu, Ognjen Rudovic, Konstantinos Bousmalis, Vladimir I. Pavlovic. 2018
193 citations recorded by the source corpus.
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world settings one seeks to adapt to multiple, but somewhat similar, target domains. Applying pairwise adaptation approaches to this setting may be suboptimal, as they fail to leverage shared information among multiple domains. In this work, we propose an information theoretic approach for domain adaptation in the novel context of multiple target domains with unlabeled instances and one source domain with labeled instances. Our model aims to find a shared latent space common to all domains, while simultaneously accounting for the remaining private, domain-specific factors. Disentanglement of shared and private information is accomplished using a unified information-theoretic approach, which also serves to establish a stronger link between the latent representations and the observed data. The resulting model, accompanied by an efficient optimization algorithm, allows simultaneous adaptation from a single source to multiple target domains. We test our approach on three challenging publicly-available datasets, showing that it outperforms several popular domain adaptation methods.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Information Theory
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
In Computer Vision and Pattern Recognition
- Dacheng Tao
- Luc Van Gool
- Xiaogang Wang
- Trevor Darrell
- Chen Change Loy
- Ming-Hsuan Yang
- Ziwei Liu
- Yi Yang
In Representation & Self-Supervised Learning
In Information Theory
Citations in the corpus
- Overcoming Negative Transfer: A Survey (2020, background): “Information sharing & Memory module [53], [54] Non-stationary Feature Incremental learning [55] Given different number of labeled instances in the target domain, a natural setting is to trade-off between minimizing the source and the target empirical errors with α ∈ [0 , 1] : Ben-David et al. [21]…”
- CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information (2020, methodology): “The semantically disentangled representations help improve the performance of deep learning models, especially in the fields of conditional generation (Ma et al., 2018), style transfer (John et al., 2019), and domain adaptation (Gholami et al., 2018).”
- Gradient Regularized Contrastive Learning for Continual Domain Adaptation (2020, background): “Most of the literature of domain adaptation focus on adapting from source domain to one target domain [1, 2, 3, 4, 5, 6] or multiple target domains [7, 8, 9].”
- A Survey of Unsupervised Deep Domain Adaptation (2018, background): “It is also possible to perform multi-target domain adaptation [77], though this case is even more rarely studied.”
- Open Compound Domain Adaptation (2019, methodology): “Table 6 summarizes the key methodological differences between MTDA [9], BTDA [5], DADA [39] and our OCDA.”
- Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation (2020, methodology): “A simultaneous adaptation to multiple and unlabeled target domains [12] from a single source domain is a worthy but unexplored DA scenario.”
- Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results (2020, methodology): “Unsupervised domain adaptation methods have been extensively studied [17], [18], [19], [20], [21], [22], [23], [24].”