Unsupervised domain adaptation with Joint Adversarial Variational AutoEncoder

Li, Yuze; Zhang, Yan; Yang, Chunling

doi:10.1016/j.knosys.2022.109065

Cited by 11 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parameters in the objective are learned through RMSProp, which is an adaptive learning rate method that divides the learning rate by an exponentially decaying average of squared gradients. We choose RMSProp as the optimizer because it is a popular and effective method to determine the learning rate abortively which is widely used for training adversarial neural networks (Dou et al, 2019 ; Li et al, 2022 ; Zhou and Pan, 2022 ). Adam is another widely adopted optimizer that extends RMSProp with momentum terms, however, the momentum terms may make Adam unstable (Mao et al, 2017 ; Luo et al, 2018 ; Clavijo et al, 2021 ).…”

Section: F Air Da: Fair Classification With Domain...mentioning

confidence: 99%

Fair classification via domain adaptation: A dual adversarial learning approach

Liang

Chen²,

Tian³

et al. 2023

Front. Big Data

View full text Add to dashboard Cite

Modern machine learning (ML) models are becoming increasingly popular and are widely used in decision-making systems. However, studies have shown critical issues of ML discrimination and unfairness, which hinder their adoption on high-stake applications. Recent research on fair classifiers has drawn significant attention to developing effective algorithms to achieve fairness and good classification performance. Despite the great success of these fairness-aware machine learning models, most of the existing models require sensitive attributes to pre-process the data, regularize the model learning or post-process the prediction to have fair predictions. However, sensitive attributes are often incomplete or even unavailable due to privacy, legal or regulation restrictions. Though we lack the sensitive attribute for training a fair model in the target domain, there might exist a similar domain that has sensitive attributes. Thus, it is important to exploit auxiliary information from a similar domain to help improve fair classification in the target domain. Therefore, in this paper, we study a novel problem of exploring domain adaptation for fair classification. We propose a new framework that can learn to adapt the sensitive attributes from a source domain for fair classification in the target domain. Extensive experiments on real-world datasets illustrate the effectiveness of the proposed model for fair classification, even when no sensitive attributes are available in the target domain.

show abstract

Section: F Air Da: Fair Classification With Domain...mentioning

confidence: 99%

Fair classification via domain adaptation: A dual adversarial learning approach

Liang

Chen²,

Tian³

et al. 2023

Front. Big Data

View full text Add to dashboard Cite

show abstract

“…In addition, there is also a domain adaptation approach [27] using generative models such as CycleGAN [28] to reduce the distance between source and target domain samples in the feature space. The unsupervised domain adaptation methods [29, 30] based on autoencoder also obtains good results. The deep learning method by autoencoder acquires different data features to improve the domain migration effect.…”

Section: Related Workmentioning

confidence: 99%

Category‐related attention domain adaptation for one‐stage cross‐domain object detection

Guan,

Dong,

Gao

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Cross‐domain object detection aims to generalize the distribution of features extracted by an object detector from an annotated domain to an unknown and unlabelled domain. Although one‐stage cross‐domain object detectors have significant advantages in deployment than two‐stage ones, they suffer from two problems. First, neglect of category features and inaccurate alignment between multiple category features would lead to decreased domain adaptation efficiency. Second, one‐stage detectors are more sensitive to imbalance of samples and negative samples severely affect the alignment process of domain adaptation. To overcome these two problems, an innovative category‐related attention domain adaptive method that refines discrimination for each category's feature has been proposed in this paper. In the proposed method, a group of domain discriminators is assigned to each category to refine the fine‐grained features between categories. The discriminators are trained via an adversarial discriminant framework to align the fine‐grained distributions cross different domains. A category attention alignment (CAA) module is proposed to navigate more attention to the foreground regions in instance‐level, which effectively alleviates the negative migration problem caused by the positive and negative sample imbalance of the one‐stage detector. Specifically, two sub‐modules in the CAA module are developed: a local CAA module and a global CAA module. These modules aim to optimize the domain offsets in both the local and global dimensions. In addition, a progressive global alignment module is designed to align image‐level features, offering prior knowledge of migration for the CAA module. The progressive global alignment module and CAA module collaboratively engage in benign competition with the backbone network across various levels. Extensive transferring experiments are conducted among cityscapes, foggy cityscapes, SIM10K, and KITTI. Experimental results show that the proposed method has much superior performance than other one‐stage cross‐domain detectors.

show abstract

“…For example, in JMVAE [17], the authors project two different views to a shared latent space in a bidirectional double VAE. Whereas, in JVA 2 E [18], they prefer to combine adversarial learning with the generative ability of the VAE's latent features. Other works, such as MVAE [19], combine K input views by having an individual encoder per view but sharing parameters between them and, later, create a common latent space representation by a Gaussian PoE given the private representations.…”

Section: Introductionmentioning

confidence: 99%

Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space

Guerrero-López¹,

Sevilla-Salcedo²,

Gómez-Verdejo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Real-world databases are complex, they usually present redundancy and shared correlations between heterogeneous and multiple representations of the same data. Thus, exploiting and disentangling shared information between views is critical. For this purpose, recent studies often fuse all views into a shared nonlinear complex latent space but they lose the interpretability. To overcome this limitation, here we propose a novel method to combine multiple Variational AutoEncoders (VAE) architectures with a Factor Analysis latent space (FA-VAE).Concretely, we use a VAE to learn a private representation of each heterogeneous view in a continuous latent space. Then, we model the shared latent space by projecting every private variable to a low-dimensional latent space using a linear projection matrix. Thus, we create an interpretable hierarchical dependency between private and shared information. This way, the novel model is able to simultaneously: (i) learn from multiple heterogeneous views, (ii) obtain an interpretable hierarchical shared space, and, (iii) perform transfer learning between generative models.

show abstract

Unsupervised domain adaptation with Joint Adversarial Variational AutoEncoder

Cited by 11 publications

References 36 publications

Fair classification via domain adaptation: A dual adversarial learning approach

Fair classification via domain adaptation: A dual adversarial learning approach

Category‐related attention domain adaptation for one‐stage cross‐domain object detection

Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space

Contact Info

Product

Resources

About