Partial Domain Adaptation

Partial domain adaptation (PDA) addresses the challenge of adapting machine learning models to target domains where only a subset of the source domain's classes are present. Current research focuses on mitigating negative transfer from irrelevant source classes, often employing adversarial learning, instance weighting, and prototype-based methods to align distributions and improve target classification accuracy. This area is significant because it enables more robust and efficient model deployment in real-world scenarios with incomplete or mismatched data, impacting applications ranging from fault diagnosis to image classification. The development of efficient and robust PDA techniques is crucial for improving the generalizability and reliability of machine learning models in diverse settings.

Papers

October 22, 2024

Co-training partial domain adaptation networks for industrial Fault Diagnosis
Gecheng Chen
Domain Adaptation Formality Transfer Fault Diagnosis Partial Domain Adaptation Adversarial Adaptation

September 16, 2024

Partial Distribution Matching via Partial Wasserstein Adversarial Networks
Zi-Ming Wang, Nan Xue, Ling Lei, Rebecka Jörnsten, Gui-Song Xia
Matching Accuracy Distribution Matching Wasserstein Generative Adversarial Network Partial Domain Adaptation

June 20, 2024

Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach
Mengcheng Lan, Min Meng, Jun Yu, Jigang Wu
LeArning Abstract Domain Adaptation Self Supervised Partial Domain Adaptation Knowledge Exploration Weakly Supervised Domain Adaptation

June 16, 2024

Physics-Informed Deep Learning and Partial Transfer Learning for Bearing Fault Diagnosis in the Presence of Highly Missing Data
Mohammadreza Kavianpour, Parisa Kavianpour, Amin Ramezani
Deep Learning Domain Adaptation Speech Presence Missing Data Physic Informed Deep Learning Fault Diagnosis Partial Domain Adaptation

December 8, 2023

A Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting
Jinjing Zhu, Feiyang Ye, Qiao Xiao, Pengxin Guo, Yu Zhang, Qiang Yang
Domain Adaptation Unified Framework Open Set Domain Adaptation Universal Domain Adaptation Instance Weighting Partial Domain Adaptation

October 18, 2023

Robust Class-Conditional Distribution Alignment for Partial Domain Adaptation
Sandipan Choudhuri, Arunabha Sen
Feature Alignment Distribution Alignment Classification Error Robust Pseudo Label Partial Domain Adaptation Target Supervision

September 7, 2023

A Robust Negative Learning Approach to Partial Domain Adaptation Using Source Prototypes
Sandipan Choudhuri, Suli Adeniye, Arunabha Sen
Complementary Label Pseudo Label Refinement Negative Learning Partial Domain Adaptation Prototype Highlighting Current Challenge Target Supervision

December 3, 2022

Domain-Invariant Feature Alignment Using Variational Inference For Partial Domain Adaptation
Sandipan Choudhuri, Suli Adeniye, Arunabha Sen, Hemanth Venkateswara
Variational Inference Open Set Domain Adaptation Partial Domain Adaptation Cross Domain Feature Alignment Cross Domain Classification

October 3, 2022

A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods
Tiago Salvador, Kilian Fatras, Ioannis Mitliagkas, Adam Oberman
Domain Adaptation Domain Sample Realistic Evaluation Partial Domain Adaptation Target Domain Image

July 17, 2022

Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation
Sandipan Choudhuri, Hemanth Venkateswara, Arunabha Sen
Domain Invariant Feature Distribution Alignment Voting Method Open Set Domain Adaptation Class Weight Partial Domain Adaptation Cross Domain Classification Weight Coupling Learning

June 7, 2022

OneRing: A Simple Method for Source-free Open-partial Domain Adaptation
Shiqi Yang, Yaxing Wang, Kai Wang, Shangling Jui, Joost van de Weijer
Unlabeled Target Domain Open Set Domain Adaptation Simple Method Partial Domain Adaptation Near Ring

April 29, 2022

Controlled Generation of Unseen Faults for Partial and Open-Partial Domain Adaptation
Katharina Rombach, Dr. Gabriel Michau, Prof. Dr. Olga Fink
Domain Adaptation Fault Detection Controllable Generation Partial Domain Adaptation

March 14, 2022

From Big to Small: Adaptive Learning to Partial-Set Domains
Zhangjie Cao, Kaichao You, Ziyang Zhang, Jianmin Wang, Mingsheng Long
Domain Adaptation Adaptive Learning Partial Domain Adaptation Pseudo Domain Target Domain Adaptation

March 1, 2022

Low-Cost On-device Partial Domain Adaptation (LoCO-PDA): Enabling efficient CNN retraining on edge devices
Aditya Rajagopal, Christos-Savvas Bouganis
Convolutional Neural Network Domain Adaptation Efficient CNN Training Data Distribution Partial Domain Adaptation

Partial Domain Adaptation

Papers

Co-training partial domain adaptation networks for industrial Fault Diagnosis

Partial Distribution Matching via Partial Wasserstein Adversarial Networks

Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach

Physics-Informed Deep Learning and Partial Transfer Learning for Bearing Fault Diagnosis in the Presence of Highly Missing Data

A Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting

Robust Class-Conditional Distribution Alignment for Partial Domain Adaptation

A Robust Negative Learning Approach to Partial Domain Adaptation Using Source Prototypes

Domain-Invariant Feature Alignment Using Variational Inference For Partial Domain Adaptation

A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods

Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation

OneRing: A Simple Method for Source-free Open-partial Domain Adaptation

Controlled Generation of Unseen Faults for Partial and Open-Partial Domain Adaptation

From Big to Small: Adaptive Learning to Partial-Set Domains

Low-Cost On-device Partial Domain Adaptation (LoCO-PDA): Enabling efficient CNN retraining on edge devices