Polycentric Clustering and Structural Regularization for Source-free
Unsupervised Domain Adaptation
- URL: http://arxiv.org/abs/2210.07463v1
- Date: Fri, 14 Oct 2022 02:20:48 GMT
- Title: Polycentric Clustering and Structural Regularization for Source-free
Unsupervised Domain Adaptation
- Authors: Xinyu Guan, Han Sun, Ningzhong Liu, Huiyu Zhou
- Abstract summary: Source-Free Domain Adaptation (SFDA) aims to solve the domain adaptation problem by transferring the knowledge learned from a pre-trained source model to an unseen target domain.
Most existing methods assign pseudo-labels to the target data by generating feature prototypes.
In this paper, a novel framework named PCSR is proposed to tackle SFDA via a novel intra-class Polycentric Clustering and Structural Regularization strategy.
- Score: 20.952542421577487
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Source-Free Domain Adaptation (SFDA) aims to solve the domain adaptation
problem by transferring the knowledge learned from a pre-trained source model
to an unseen target domain. Most existing methods assign pseudo-labels to the
target data by generating feature prototypes. However, due to the discrepancy
in the data distribution between the source domain and the target domain and
category imbalance in the target domain, there are severe class biases in the
generated feature prototypes and noisy pseudo-labels. Besides, the data
structure of the target domain is often ignored, which is crucial for
clustering. In this paper, a novel framework named PCSR is proposed to tackle
SFDA via a novel intra-class Polycentric Clustering and Structural
Regularization strategy. Firstly, an inter-class balanced sampling strategy is
proposed to generate representative feature prototypes for each class.
Furthermore, k-means clustering is introduced to generate multiple clustering
centers for each class in the target domain to obtain robust pseudo-labels.
Finally, to enhance the model's generalization, structural regularization is
introduced for the target domain. Extensive experiments on three UDA benchmark
datasets show that our method performs better or similarly against the other
state of the art methods, demonstrating our approach's superiority for visual
domain adaptation problems.
Related papers
- Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation [108.40945109477886]
We propose a novel SSDA approach named Graph-based Adaptive Betweenness Clustering (G-ABC) for achieving categorical domain alignment.
Our method outperforms previous state-of-the-art SSDA approaches, demonstrating the superiority of the proposed G-ABC algorithm.
arXiv Detail & Related papers (2024-01-21T09:57:56Z) - Unsupervised Domain Adaptation via Distilled Discriminative Clustering [45.39542287480395]
We re-cast the domain adaptation problem as discriminative clustering of target data.
We propose to jointly train the network using parallel, supervised learning objectives over labeled source data.
We conduct careful ablation studies and extensive experiments on five popular benchmark datasets.
arXiv Detail & Related papers (2023-02-23T13:03:48Z) - A Prototype-Oriented Clustering for Domain Shift with Source Privacy [66.67700676888629]
We introduce Prototype-oriented Clustering with Distillation (PCD) to improve the performance and applicability of existing methods.
PCD first constructs a source clustering model by aligning the distributions of prototypes and data.
It then distills the knowledge to the target model through cluster labels provided by the source model while simultaneously clustering the target data.
arXiv Detail & Related papers (2023-02-08T00:15:35Z) - BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy
for Source-free Domain Adaptation [74.93176783541332]
Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data.
To make up for the absence of source data, most existing methods introduced feature prototype based pseudo-labeling strategies.
We propose a general class-Balanced Multicentric Dynamic prototype strategy for the SFDA task.
arXiv Detail & Related papers (2022-04-06T13:23:02Z) - Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation [85.6961770631173]
In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them.
We propose a novel approach called Cross-domain Adaptive Clustering to address this problem.
arXiv Detail & Related papers (2021-04-19T16:07:32Z) - 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) - Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain
Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain.
We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one.
Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
arXiv Detail & Related papers (2020-12-08T08:52:00Z) - 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)
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.