Dynamic Feature Alignment for Semi-supervised Domain Adaptation
- URL: http://arxiv.org/abs/2110.09641v1
- Date: Mon, 18 Oct 2021 22:26:27 GMT
- Title: Dynamic Feature Alignment for Semi-supervised Domain Adaptation
- Authors: Yu Zhang, Gongbo Liang, Nathan Jacobs
- Abstract summary: We propose to use dynamic feature alignment to address both inter- and intra-domain discrepancy.
Our approach, which doesn't require extensive tuning or adversarial training, significantly improves the state of the art for semi-supervised domain adaptation.
- Score: 23.67093835143
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Most research on domain adaptation has focused on the purely unsupervised
setting, where no labeled examples in the target domain are available. However,
in many real-world scenarios, a small amount of labeled target data is
available and can be used to improve adaptation. We address this
semi-supervised setting and propose to use dynamic feature alignment to address
both inter- and intra-domain discrepancy. Unlike previous approaches, which
attempt to align source and target features within a mini-batch, we propose to
align the target features to a set of dynamically updated class prototypes,
which we use both for minimizing divergence and pseudo-labeling. By updating
based on class prototypes, we avoid problems that arise in previous approaches
due to class imbalances. Our approach, which doesn't require extensive tuning
or adversarial training, significantly improves the state of the art for
semi-supervised domain adaptation. We provide a quantitative evaluation on two
standard datasets, DomainNet and Office-Home, and performance analysis.
Related papers
- Labeling Where Adapting Fails: Cross-Domain Semantic Segmentation with
Point Supervision via Active Selection [81.703478548177]
Training models dedicated to semantic segmentation require a large amount of pixel-wise annotated data.
Unsupervised domain adaptation approaches aim at aligning the feature distributions between the labeled source and the unlabeled target data.
Previous works attempted to include human interactions in this process under the form of sparse single-pixel annotations in the target data.
We propose a new domain adaptation framework for semantic segmentation with annotated points via active selection.
arXiv Detail & Related papers (2022-06-01T01:52:28Z) - Domain Generalisation for Object Detection under Covariate and Concept Shift [10.32461766065764]
Domain generalisation aims to promote the learning of domain-invariant features while suppressing domain-specific features.
An approach to domain generalisation for object detection is proposed, the first such approach applicable to any object detection architecture.
arXiv Detail & Related papers (2022-03-10T11:14:18Z) - AFAN: Augmented Feature Alignment Network for Cross-Domain Object
Detection [90.18752912204778]
Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications.
We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training.
Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
arXiv Detail & Related papers (2021-06-10T05:01:20Z) - Instance Level Affinity-Based Transfer for Unsupervised Domain
Adaptation [74.71931918541748]
We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA.
We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process.
We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
arXiv Detail & Related papers (2021-04-03T01:33:14Z) - Dynamic Domain Adaptation for Efficient Inference [12.713628738434881]
Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain.
Most prior DA approaches leverage complicated and powerful deep neural networks to improve the adaptation capacity.
We propose a dynamic domain adaptation (DDA) framework, which can simultaneously achieve efficient target inference in low-resource scenarios.
arXiv Detail & Related papers (2021-03-26T08:53:16Z) - Domain Adaptation for Semantic Parsing [68.81787666086554]
We propose a novel semantic for domain adaptation, where we have much fewer annotated data in the target domain compared to the source domain.
Our semantic benefits from a two-stage coarse-to-fine framework, thus can provide different and accurate treatments for the two stages.
Experiments on a benchmark dataset show that our method consistently outperforms several popular domain adaptation strategies.
arXiv Detail & Related papers (2020-06-23T14:47:41Z) - Cross-domain Detection via Graph-induced Prototype Alignment [114.8952035552862]
We propose a Graph-induced Prototype Alignment (GPA) framework to seek for category-level domain alignment.
In addition, in order to alleviate the negative effect of class-imbalance on domain adaptation, we design a Class-reweighted Contrastive Loss.
Our approach outperforms existing methods with a remarkable margin.
arXiv Detail & Related papers (2020-03-28T17:46:55Z) - Domain Adaptation by Class Centroid Matching and Local Manifold
Self-Learning [8.316259570013813]
We propose a novel domain adaptation approach, which can thoroughly explore the data distribution structure of target domain.
We regard the samples within the same cluster in target domain as a whole rather than individuals and assigns pseudo-labels to the target cluster by class centroid matching.
An efficient iterative optimization algorithm is designed to solve the objective function of our proposal with theoretical convergence guarantee.
arXiv Detail & Related papers (2020-03-20T16:59:27Z) - Enlarging Discriminative Power by Adding an Extra Class in Unsupervised
Domain Adaptation [5.377369521932011]
We propose an idea of empowering the discriminativeness: Adding a new, artificial class and training the model on the data together with the GAN-generated samples of the new class.
Our idea is highly generic so that it is compatible with many existing methods such as DANN, VADA, and DIRT-T.
arXiv Detail & Related papers (2020-02-19T07:58:24Z) - Bi-Directional Generation for Unsupervised Domain Adaptation [61.73001005378002]
Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information.
Conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure.
We propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
arXiv Detail & Related papers (2020-02-12T09:45:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.