Multi-Target Domain Adaptation with Collaborative Consistency Learning
- URL: http://arxiv.org/abs/2106.03418v1
- Date: Mon, 7 Jun 2021 08:36:20 GMT
- Title: Multi-Target Domain Adaptation with Collaborative Consistency Learning
- Authors: Takashi Isobe, Xu Jia, Shuaijun Chen, Jianzhong He, Yongjie Shi,
Jianzhuang Liu, Huchuan Lu, Shengjin Wang
- Abstract summary: We propose a collaborative learning framework to achieve unsupervised multi-target domain adaptation.
The proposed method can effectively exploit rich structured information contained in both labeled source domain and multiple unlabeled target domains.
- Score: 105.7615147382486
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently unsupervised domain adaptation for the semantic segmentation task
has become more and more popular due to high-cost of pixel-level annotation on
real-world images. However, most domain adaptation methods are only restricted
to single-source-single-target pair, and can not be directly extended to
multiple target domains. In this work, we propose a collaborative learning
framework to achieve unsupervised multi-target domain adaptation. An
unsupervised domain adaptation expert model is first trained for each
source-target pair and is further encouraged to collaborate with each other
through a bridge built between different target domains. These expert models
are further improved by adding the regularization of making the consistent
pixel-wise prediction for each sample with the same structured context. To
obtain a single model that works across multiple target domains, we propose to
simultaneously learn a student model which is trained to not only imitate the
output of each expert on the corresponding target domain, but also to pull
different expert close to each other with regularization on their weights.
Extensive experiments demonstrate that the proposed method can effectively
exploit rich structured information contained in both labeled source domain and
multiple unlabeled target domains. Not only does it perform well across
multiple target domains but also performs favorably against state-of-the-art
unsupervised domain adaptation methods specially trained on a single
source-target pair
Related papers
- Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from
Mixture-of-Experts [33.21435044949033]
Most existing methods perform training on multiple source domains using a single model.
We propose a novel framework for unsupervised test-time adaptation, which is formulated as a knowledge distillation process.
arXiv Detail & Related papers (2022-10-08T02:28:10Z) - MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization [55.06956781674986]
We resort to solving the semi-supervised domain generalization task, where there are a few label information in each source domain.
We propose MultiMatch, extending FixMatch to the multi-task learning framework, producing the high-quality pseudo-label for SSDG.
A series of experiments validate the effectiveness of the proposed method, and it outperforms the existing semi-supervised methods and the SSDG method on several benchmark DG datasets.
arXiv Detail & Related papers (2022-08-11T14:44:33Z) - ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for
Open Compound Domain Adaptation in Semantic Segmentation [78.19743899703052]
Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous.
We introduce a multi-teacher framework with bidirectional photometric mixing to adapt to every target subdomain.
We conduct an adaptive distillation to learn a student model and apply consistency regularization to improve the student generalization.
arXiv Detail & Related papers (2022-07-19T03:30:48Z) - META: Mimicking Embedding via oThers' Aggregation for Generalizable
Person Re-identification [68.39849081353704]
Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time.
This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
arXiv Detail & Related papers (2021-12-16T08:06:50Z) - Reiterative Domain Aware Multi-target Adaptation [14.352214079374463]
We propose Reiterative D-CGCT (RD-CGCT) that obtains better adaptation performance by reiterating multiple times over each target domain.
RD-CGCT significantly improves the performance over D-CGCT for Office-Home and Office31 datasets.
arXiv Detail & Related papers (2021-08-26T17:12:25Z) - Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic
Segmentation [32.39557675340562]
We address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains.
We introduce two adversarial frameworks: (i) multi-discriminator, which explicitly aligns each target domain to its counterparts, and (ii) multi-target knowledge transfer, which learns a target-agnostic model.
In all tested scenarios, our approaches consistently outperform baselines, setting competitive standards for the novel task.
arXiv Detail & Related papers (2021-08-16T08:36:10Z) - Domain Consistency Regularization for Unsupervised Multi-source Domain
Adaptive Classification [57.92800886719651]
Deep learning-based multi-source unsupervised domain adaptation (MUDA) has been actively studied in recent years.
domain shift in MUDA exists not only between the source and target domains but also among multiple source domains.
We propose an end-to-end trainable network that exploits domain Consistency Regularization for unsupervised Multi-source domain Adaptive classification.
arXiv Detail & Related papers (2021-06-16T07:29:27Z) - Multi-Source Domain Adaptation with Collaborative Learning for Semantic
Segmentation [32.95273803359897]
Multi-source unsupervised domain adaptation(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain.
We propose a novel multi-source domain adaptation framework based on collaborative learning for semantic segmentation.
arXiv Detail & Related papers (2021-03-08T12:51:42Z) - Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain
Adaptive Semantic Segmentation [102.42638795864178]
We propose a principled meta-learning based approach to OCDA for semantic segmentation.
We cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner.
A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code.
We learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization.
arXiv Detail & Related papers (2020-12-15T13:21:54Z) - Contradistinguisher: A Vapnik's Imperative to Unsupervised Domain
Adaptation [7.538482310185133]
We propose a model referred Contradistinguisher that learns contrastive features and whose objective is to jointly learn to contradistinguish the unlabeled target domain in an unsupervised way.
We achieve the state-of-the-art on Office-31 and VisDA-2017 datasets in both single-source and multi-source settings.
arXiv Detail & Related papers (2020-05-25T19:54:38Z)
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.