• Home
  • Search
  • Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
  • Cite Icon150
  • https://doi.org/10.24963/ijcai.2021/402Copy DOI Icon

Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation

  • Aug 1, 2021
  • Zhen Qiu +6 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We study a practical domain adaptation task, called source-free unsupervised domain adaptation (UDA) problem, in which we cannot access source domain data due to data privacy issues but only a pre-trained source model and unlabeled target data are available. This task, however, is very difficult due to one key challenge: the lack of source data and target domain labels makes model adaptation very challenging. To address this, we propose to mine the hidden knowledge in the source model and exploit it to generate source avatar prototypes (i.e. representative features for each source class) as well as target pseudo labels for domain alignment. To this end, we propose a Contrastive Prototype Generation and Adaptation (CPGA) method. Specifically, CPGA consists of two stages: (1) prototype generation: by exploring the classification boundary information of the source model, we train a prototype generator to generate avatar prototypes via contrastive learning. (2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes. Extensive experiments on three UDA benchmark datasets demonstrate the effectiveness and superiority of the proposed method.

Similar Papers
  • Book Chapter
  • Citations94

Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling

  • Jan 01, 2021
  • Cheng Chen +4
  • Research Article

Adaptive integrated weight unsupervised multi-source domain adaptation without source data

  • Apr 22, 2025
  • Complex & Intelligent Systems
  • Zhirui Wang +2
  • Research Article
  • Citations15

Unsupervised domain adaptation without source data for estimating occupancy and recognizing activities in smart buildings

  • Dec 01, 2023
  • Energy and Buildings
  • Jawher Dridi +2
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • PDF
  • Research Article
  • Citations9

Adversarial Learning and Interpolation Consistency for Unsupervised Domain Adaptation

  • Jan 01, 2019
  • IEEE Access
  • Xin Zhao +1
  • PDF
  • Research Article
  • Citations3

SFDA-CD: A Source-Free Unsupervised Domain Adaptation for VHR Image Change Detection

  • Apr 04, 2024
  • Remote Sensing
  • Jingxuan Wang +1
  • PDF
  • Research Article
  • Citations5

On the Importance of Attention and Augmentations for Hypothesis Transfer in Domain Adaptation and Generalization

  • Oct 12, 2023
  • Sensors (Basel, Switzerland)
  • Rajat Sahay +5
  • Research Article
  • Citations45

A Source-Free Domain Adaptive Polyp Detection Framework With Style Diversification Flow.

  • Jul 01, 2022
  • IEEE Transactions on Medical Imaging
  • Xinyu Liu +1
  • Conference Article
  • Citations25

Self-Adaptation for Unsupervised Domain Adaptation

  • Oct 22, 2019
  • Xia Cui +1
  • Conference Article
  • Citations78

SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation

  • Jan 01, 2021
  • Hao-Wei Yeh +3
  • Research Article
  • Citations316

Domain Adaptive Ensemble Learning.

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Kaiyang Zhou +3
  • Research Article
  • Citations145

Aggregating Randomized Clustering-Promoting Invariant Projections for Domain Adaptation.

  • May 01, 2018
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Jian Liang +3
  • Conference Article
  • Citations9

Online Domain Adaptation for Person Re-Identification with a Human in the Loop

  • Jan 10, 2021
  • Rita Delussu +3
  • Research Article

Robust Source-Free Domain Adaptation From Non-Robust Source Models.

  • Jan 01, 2026
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Yao Xiao +4
  • Research Article
  • Citations43

Pseudo Labels for Unsupervised Domain Adaptation: A Review

  • Aug 03, 2023
  • Electronics
  • Yundong Li +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.