Multi-level Consistency Learning for Semi-supervised Domain Adaptation

05/09/2022
by   Zizheng Yan, et al.
0

Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. Specifically, our MCL regularizes the consistency of different views of target domain samples at three levels: (i) at inter-domain level, we robustly and accurately align the source and target domains using a prototype-based optimal transport method that utilizes the pros and cons of different views of target samples; (ii) at intra-domain level, we facilitate the learning of both discriminative and compact target feature representations by proposing a novel class-wise contrastive clustering loss; (iii) at sample level, we follow standard practice and improve the prediction accuracy by conducting a consistency-based self-training. Empirically, we verified the effectiveness of our MCL framework on three popular SSDA benchmarks, i.e., VisDA2017, DomainNet, and Office-Home datasets, and the experimental results demonstrate that our MCL framework achieves the state-of-the-art performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/04/2023

Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning

In semi-supervised domain adaptation (SSDA), a few labeled target sample...
research
12/04/2020

Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation

Semi-supervised domain adaptation (SSDA) methods have demonstrated great...
research
07/07/2023

Universal Semi-supervised Model Adaptation via Collaborative Consistency Training

In this paper, we introduce a realistic and challenging domain adaptatio...
research
04/04/2022

Con^2DA: Simplifying Semi-supervised Domain Adaptation by Learning Consistent and Contrastive Feature Representations

In this work, we present Con^2DA, a simple framework that extends recent...
research
02/10/2022

Consistency and Diversity induced Human Motion Segmentation

Subspace clustering is a classical technique that has been widely used f...
research
06/18/2021

Semi-supervised Optimal Transport with Self-paced Ensemble for Cross-hospital Sepsis Early Detection

The utilization of computer technology to solve problems in medical scen...
research
03/21/2019

Multi-Domain Adversarial Learning

Multi-domain learning (MDL) aims at obtaining a model with minimal avera...

Please sign up or login with your details

Forgot password? Click here to reset