Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation

By Yen-Cheng Liu, Yu-Ying Yeh, Tzu-Chien Fu, Sheng-De Wang, Wei-Chen Chiu, Yu-Chiang Frank Wang. 2017

117 citations recorded by the source corpus.

While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However, one cannot easily address this task without observing ground truth annotation for the training data. To address this problem, we propose a novel deep learning model of Cross-Domain Representation Disentangler (CDRD). By observing fully annotated source-domain data and unlabeled target-domain data of interest, our model bridges the information across data domains and transfers the attribute information accordingly. Thus, cross-domain feature disentanglement and adaptation can be jointly performed. In the experiments, we provide qualitative results to verify our disentanglement capability. Moreover, we further confirm that our model can be applied for solving classification tasks of unsupervised domain adaptation, and performs favorably against state-of-the-art image disentanglement and translation 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

In Computer Vision and Pattern Recognition

Citations in the corpus

On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset (2019, background): “Using some sort of supervision [e.g. 43, 4, 35, 40, 9] or proposing completely unsupervised [e.g. 19, 24, 7, 27, 13] learning approaches.”
Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness (2018, background): “…more structure imposing regularization have been made, either with some sort of supervision (e.g. Siddharth et al., 2017; Bouchacourt et al., 2017; Liu et al., 2017; Mathieu et al., 2016; Cheung et al., 2014) or completely unsupervised (e.g. Higgins et al., 2017; Kim & Mnih, 2018; Chen et al.,…”
Recent Advances in Autoencoder-Based Representation Learning (2018, methodology): “We conclude the review section by an overview of related methods such as cross-domain representation learning [27–29] in Section 6.”
Interventional Robustness of Deep Latent Variable Models (2018, background): “…such structure imposing regularization have been made, either with some sort of supervision (e.g. Siddharth et al., 2017; Bouchacourt et al., 2017; Liu et al., 2017; Mathieu et al., 2016; Cheung et al., 2014) or completely unsupervised (e.g. Higgins et al., 2017; Kim and Mnih, 2018; Chen et al.,…”
Separate to Adapt: Open Set Domain Adaptation via Progressive Separation (2019, methodology): “Existing domain adaptation methods seek to bridge domain gap by distribution matching in feature-level [36, 4, 17, 19, 35, 3] or in pixellevel [10, 31, 11, 22, 16].”
Domain Agnostic Learning with Disentangled Representations (2019, methodology): “Recent work attempts to disentangle features in the latent space of autoencoders with adversarial training (Cao et al., 2018; Liu et al., 2018b; Odena et al., 2017; Lee et al., 2018).”
Image-to-image translation for cross-domain disentanglement (2018, background): “Finally, some domain adaptation approaches [8, 9, 16, 29] aim at obtaining invariant features for the classification task, granting some level of disentanglement but depending on class labels.”
A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation (2018, methodology): “Table 2 provides quantitative evaluation on the recovered images using our proposed UFDN with E-CDRD [18] and StarGAN 3 [4].”
Universal Domain Adaptation (2019, methodology): “Methods based on generative models synthesize labeled target samples as data augmentation and match domains in both pixel and feature levels [19, 36, 16, 20, 26, 17, 41].”
Guided Variational Autoencoder for Disentanglement Learning (2020, methodology): “Existing approaches [38, 37] impose supervision as a conditional model for an image translation task, whereas our supervised Guided-VAE model targets the generic generative modeling task by using an adversarial excitation and inhibition formulation.”