Variational Model Perturbation for Source-Free Domain Adaptation
- URL: http://arxiv.org/abs/2210.10378v1
- Date: Wed, 19 Oct 2022 08:41:19 GMT
- Title: Variational Model Perturbation for Source-Free Domain Adaptation
- Authors: Mengmeng Jing, Xiantong Zhen, Jingjing Li and Cees G. M. Snoek
- Abstract summary: We introduce perturbations into the model parameters by variational Bayesian inference in a probabilistic framework.
We demonstrate the theoretical connection to learning Bayesian neural networks, which proves the generalizability of the perturbed model to target domains.
- Score: 64.98560348412518
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We aim for source-free domain adaptation, where the task is to deploy a model
pre-trained on source domains to target domains. The challenges stem from the
distribution shift from the source to the target domain, coupled with the
unavailability of any source data and labeled target data for optimization.
Rather than fine-tuning the model by updating the parameters, we propose to
perturb the source model to achieve adaptation to target domains. We introduce
perturbations into the model parameters by variational Bayesian inference in a
probabilistic framework. By doing so, we can effectively adapt the model to the
target domain while largely preserving the discriminative ability. Importantly,
we demonstrate the theoretical connection to learning Bayesian neural networks,
which proves the generalizability of the perturbed model to target domains. To
enable more efficient optimization, we further employ a parameter sharing
strategy, which substantially reduces the learnable parameters compared to a
fully Bayesian neural network. Our model perturbation provides a new
probabilistic way for domain adaptation which enables efficient adaptation to
target domains while maximally preserving knowledge in source models.
Experiments on several source-free benchmarks under three different evaluation
settings verify the effectiveness of the proposed variational model
perturbation for source-free domain adaptation.
Related papers
- 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) - Mitigate Domain Shift by Primary-Auxiliary Objectives Association for
Generalizing Person ReID [39.98444065846305]
ReID models struggle in learning domain-invariant representation solely through training on an instance classification objective.
We introduce a method that guides model learning of the primary ReID instance classification objective by a concurrent auxiliary learning objective on weakly labeled pedestrian saliency detection.
Our model can be extended with the recent test-time diagram to form the PAOA+, which performs on-the-fly optimization against the auxiliary objective.
arXiv Detail & Related papers (2023-10-24T15:15:57Z) - Rethinking the Role of Pre-Trained Networks in Source-Free Domain
Adaptation [26.481422574715126]
Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to an unlabeled target domain.
Large-data pre-trained networks are used to initialize source models during source training, and subsequently discarded.
We propose to integrate the pre-trained network into the target adaptation process as it has diversified features important for generalization.
arXiv Detail & Related papers (2022-12-15T02:25:22Z) - Fast OT for Latent Domain Adaptation [25.915629674463286]
We propose an algorithm that uses optimal transport theory with a verifiably efficient and implementable solution to learn the best latent feature representation.
This is achieved by minimizing the cost of transporting the samples from the target domain to the distribution of the source domain.
arXiv Detail & Related papers (2022-10-02T10:25:12Z) - Uncertainty-guided Source-free Domain Adaptation [77.3844160723014]
Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model.
We propose quantifying the uncertainty in the source model predictions and utilizing it to guide the target adaptation.
arXiv Detail & Related papers (2022-08-16T08:03:30Z) - Approximate Bayesian Optimisation for Neural Networks [6.921210544516486]
A body of work has been done to automate machine learning algorithm to highlight the importance of model choice.
The necessity to solve the analytical tractability and the computational feasibility in a idealistic fashion enables to ensure the efficiency and the applicability.
arXiv Detail & Related papers (2021-08-27T19:03:32Z) - Gradual Domain Adaptation via Self-Training of Auxiliary Models [50.63206102072175]
Domain adaptation becomes more challenging with increasing gaps between source and target domains.
We propose self-training of auxiliary models (AuxSelfTrain) that learns models for intermediate domains.
Experiments on benchmark datasets of unsupervised and semi-supervised domain adaptation verify its efficacy.
arXiv Detail & Related papers (2021-06-18T03:15:25Z) - Selecting Treatment Effects Models for Domain Adaptation Using Causal
Knowledge [82.5462771088607]
We propose a novel model selection metric specifically designed for ITE methods under the unsupervised domain adaptation setting.
In particular, we propose selecting models whose predictions of interventions' effects satisfy known causal structures in the target domain.
arXiv Detail & Related papers (2021-02-11T21:03:14Z) - Do We Really Need to Access the Source Data? Source Hypothesis Transfer
for Unsupervised Domain Adaptation [102.67010690592011]
Unsupervised adaptationUDA (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain.
Prior UDA methods typically require to access the source data when learning to adapt the model.
This work tackles a practical setting where only a trained source model is available and how we can effectively utilize such a model without source data to solve UDA problems.
arXiv Detail & Related papers (2020-02-20T03:13:58Z)
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.