Dynamic Transfer for Multi-Source Domain Adaptation
- URL: http://arxiv.org/abs/2103.10583v1
- Date: Fri, 19 Mar 2021 01:22:12 GMT
- Title: Dynamic Transfer for Multi-Source Domain Adaptation
- Authors: Yunsheng Li, Lu Yuan, Yinpeng Chen, Pei Wang, Nuno Vasconcelos
- Abstract summary: We present dynamic transfer to address domain conflicts, where the model parameters are adapted to samples.
It breaks down source domain barriers and turns multi-source domains into a single-source domain.
Experimental results show that, without using domain labels, our dynamic transfer outperforms the state-of-the-art method by more than 3%.
- Score: 82.54405157719641
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent works of multi-source domain adaptation focus on learning a
domain-agnostic model, of which the parameters are static. However, such a
static model is difficult to handle conflicts across multiple domains, and
suffers from a performance degradation in both source domains and target
domain. In this paper, we present dynamic transfer to address domain conflicts,
where the model parameters are adapted to samples. The key insight is that
adapting model across domains is achieved via adapting model across samples.
Thus, it breaks down source domain barriers and turns multi-source domains into
a single-source domain. This also simplifies the alignment between source and
target domains, as it only requires the target domain to be aligned with any
part of the union of source domains. Furthermore, we find dynamic transfer can
be simply modeled by aggregating residual matrices and a static convolution
matrix. Experimental results show that, without using domain labels, our
dynamic transfer outperforms the state-of-the-art method by more than 3% on the
large multi-source domain adaptation datasets -- DomainNet. Source code is at
https://github.com/liyunsheng13/DRT.
Related papers
- Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation [40.667166043101076]
We propose a small adapter for rectifying diverse target domain styles to the source domain.
The adapter is trained to rectify the image features from diverse synthesized target domains to align with the source domain.
Our method achieves promising results on cross-domain few-shot semantic segmentation tasks.
arXiv Detail & Related papers (2024-04-16T07:07:40Z) - Revisiting the Domain Shift and Sample Uncertainty in Multi-source
Active Domain Transfer [69.82229895838577]
Active Domain Adaptation (ADA) aims to maximally boost model adaptation in a new target domain by actively selecting a limited number of target data to annotate.
This setting neglects the more practical scenario where training data are collected from multiple sources.
This motivates us to target a new and challenging setting of knowledge transfer that extends ADA from a single source domain to multiple source domains.
arXiv Detail & Related papers (2023-11-21T13:12:21Z) - Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher [11.616494893839757]
Adapting visual object detectors to operational target domains is a challenging task, commonly achieved using unsupervised domain adaptation (UDA) methods.
Recent studies have shown that when the labeled dataset comes from multiple source domains, treating them as separate domains improves the accuracy and robustness over blending these source domains and performing a UDA.
This paper proposes a novel MSDA method called Prototype-based Mean Teacher (PMT), which uses class prototypes instead of domain-specifics to encode domain-specific information.
arXiv Detail & Related papers (2023-09-26T14:08:03Z) - Dynamic Instance Domain Adaptation [109.53575039217094]
Most studies on unsupervised domain adaptation assume that each domain's training samples come with domain labels.
We develop a dynamic neural network with adaptive convolutional kernels to generate instance-adaptive residuals to adapt domain-agnostic deep features to each individual instance.
Our model, dubbed DIDA-Net, achieves state-of-the-art performance on several commonly used single-source and multi-source UDA datasets.
arXiv Detail & Related papers (2022-03-09T20:05:54Z) - VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation [26.959377850768423]
Domain adaptation aims to leverage a label-rich domain (the source domain) to help model learning in a label-scarce domain (the target domain)
Access to the source domain samples may not always be feasible in the real world applications due to different problems.
We propose a novel approach referred to as Virtual Domain Modeling (VDM-DA)
arXiv Detail & Related papers (2021-03-26T09:56:40Z) - Mutual Learning Network for Multi-Source Domain Adaptation [73.25974539191553]
We propose a novel multi-source domain adaptation method, Mutual Learning Network for Multiple Source Domain Adaptation (ML-MSDA)
Under the framework of mutual learning, the proposed method pairs the target domain with each single source domain to train a conditional adversarial domain adaptation network as a branch network.
The proposed method outperforms the comparison methods and achieves the state-of-the-art performance.
arXiv Detail & Related papers (2020-03-29T04:31:43Z) - Deep Domain-Adversarial Image Generation for Domain Generalisation [115.21519842245752]
Machine learning models typically suffer from the domain shift problem when trained on a source dataset and evaluated on a target dataset of different distribution.
To overcome this problem, domain generalisation (DG) methods aim to leverage data from multiple source domains so that a trained model can generalise to unseen domains.
We propose a novel DG approach based on emphDeep Domain-Adversarial Image Generation (DDAIG)
arXiv Detail & Related papers (2020-03-12T23:17:47Z) - MADAN: Multi-source Adversarial Domain Aggregation Network for Domain
Adaptation [58.38749495295393]
Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain.
Recent multi-source domain adaptation (MDA) methods do not consider the pixel-level alignment between sources and target.
We propose a novel MDA framework to address these challenges.
arXiv Detail & Related papers (2020-02-19T21:22:00Z)
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.