Deep Least Squares Alignment for Unsupervised Domain Adaptation
Not on the map. Why?
Abstract (arXiv)
Unsupervised domain adaptation leverages rich information from a labeled source domain to model an unlabeled target domain. Existing methods attempt to align the cross-domain distributions. However, the statistical representations of the alignment of the two domains are not well addressed. In this paper, we propose deep least squares alignment (DLSA) to estimate the distribution of the two domains in a latent space by parameterizing a linear model. We further develop marginal and conditional adaptation loss to reduce the domain discrepancy by minimizing the angle between fitting lines and intercept differences and further learning domain invariant features. Extensive experiments demonstrate that the proposed DLSA model is effective in aligning domain distributions and outperforms state-of-the-art methods.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 3 Nov 2021.
Builds on
33 of 52 references.
References · 33
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
- 2017Adversarial Discriminative Domain Adaptationcited by 1,309
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
- 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
- 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
- 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
- 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
- 2017VisDA: The Visual Domain Adaptation Challengecited by 432
21 more
- 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
- 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
- 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
- 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
- 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
- 2020Dual Mixup Regularized Learning for Adversarial Domain Adaptationcited by 99
- 2018Visual Domain Adaptation with Manifold Embedded Distribution Alignmentcited by 91
- 2019Discriminative Adversarial Domain Adaptationcited by 74
- 2019Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labelingcited by 53
- 2014Domain Adaptive Neural Networks for Object Recognitioncited by 51
- 2017Joint Geometrical and Statistical Alignment for Visual Domain Adaptationcited by 43
- 2020Domain Conditioned Adaptation Networkcited by 43
- 2019On Minimum Discrepancy Estimation for Deep Domain Adaptationcited by 34
- 2020Unsupervised Domain Adaptation via Discriminative Manifold Propagationcited by 33
- 2018Adversarial Teacher-Student Learning for Unsupervised Domain Adaptationcited by 27
- 2020Impact of ImageNet Model Selection on Domain Adaptationcited by 15
- 2021Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptationcited by 9
- 2019Modified Distribution Alignment for Domain Adaptation with Pre-trained Inception ResNetcited by 5
- 2020Adversarial Consistent Learning on Partial Domain Adaptation of PlantCLEF 2020 Challengecited by 5
- 2021Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptationcited by 4
- 2021Enhanced Separable Disentanglement for Unsupervised Domain Adaptationcited by 4
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 1.
3 papers.