Domain Impression: A Source Data Free Domain Adaptation Method

2021/02/17 by Vinod K Kurmi, Kurmi, Vinod K, Venkatesh K Subramanian +5 · 8 citations
Computer Science · Medicine · #Artificial intelligence #Bottleneck #COVID-19 diagnosis using AI #Classifier (UML) #Computer science #Data mining #Domain Adaptation and Few-Shot Learning #Domain adaptation #Impression #Machine learning #Multimodal Machine Learning Applications #Pattern recognition (psychology) #cs.AI #cs.CV

paper · pdf · doi:10.48550/arxiv.2102.09003

published in arXiv (Cornell University) (Cornell University) · Published- WACV-2021

arxiv created 2021/02/17 · openalex publication_date 2021/02/17 · arxiv updated 2021/02/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Unsupervised Domain adaptation methods solve the adaptation problem for an unlabeled target set, assuming that the source dataset is available with all labels. However, the availability of actual source samples is not always possible in practical cases. It could be due to memory constraints, privacy concerns, and challenges in sharing data. This practical scenario creates a bottleneck in the domain adaptation problem. This paper addresses this challenging scenario by proposing a domain adaptation technique that does not need any source data. Instead of the source data, we are only provided with a classifier that is trained on the source data. Our proposed approach is based on a generative framework, where the trained classifier is used for generating samples from the source classes. We learn the joint distribution of data by using the energy-based modeling of the trained classifier. At the same time, a new classifier is also adapted for the target domain. We perform various ablation analysis under different experimental setups and demonstrate that the proposed approach achieves better results than the baseline models in this extremely novel scenario.

Citations

• Deep Domain Confusion: Maximizing for Domain Invariance
• Gradient-based learning applied to document recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Cited by

• Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
• Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
• Robust Source-Free Domain Adaptation for Medical Image Segmentation based on Curriculum Learning
• A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation
• Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
• Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning
• Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation
• Topology-Aware Neighborhood Learning for Source-Free Cross-Scene Hyperspectral Image Classification

Related

• Universal Source-Free Domain Adaptation
• Casting a BAIT for Offline and Online Source-free Domain Adaptation
• Unsupervised Domain Adaptation in the Absence of Source Data
• Source-Free Unsupervised Domain Adaptation: A Survey
• Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation