• Home
  • Search
  • Source-Style Transferred Mean Teacher for Source-data Free Object Detection
  • Open Access IconOpen Access
  • Cite Icon9
  • https://doi.org/10.1145/3469877.3490584Copy DOI Icon

Source-Style Transferred Mean Teacher for Source-data Free Object Detection

  • Dec 1, 2021
  • Dan Zhang +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Unsupervised cross-domain object detection transfers a detection model trained on a source domain to the target domain that has a different data distribution from the source domain. Conventional domain adaptation detection protocols need source domain data during adaptation. However, due to some reasons such as data security, privacy and storage, we cannot access the source data in many practical applications. In this paper, we focus on source-data free domain adaptive object detection, which uses the pre-trained source model instead of the source data for cross-domain adaptation. Due to the lack of source data, we cannot directly align domain distribution between domains. To challenge this, we propose the Source style transferred Mean Teacher (SMT) for source-data free Object Detection. The batch normalization layers in the pre-trained model contain the style information and the data distribution of the non-observed source data. Thus we use the batch normalization information from the pre-trained source model to transfer the target domain feature to the source-like style feature to make full use of the knowledge from the pre-trained source model. Meanwhile, we use the consistent regularization of the Mean Teacher to further distill the knowledge from the source domain to the target domain. Furthermore, we found that by adding perturbations associated with the target domain distribution, the model can increase the robustness of domain-specific information, thus making the learned model generalized to the target domain. Experiments on multiple domain adaptation object detection benchmarks verify that our method is able to achieve state-of-the-art performance.

Similar Papers
  • Research Article
  • Citations16

Overcoming learning bias via Prototypical Feature Compensation for source-free domain adaptation

  • Sep 17, 2024
  • Pattern Recognition
  • Zicheng Pan +3
  • Research Article

Systematic Analysis of Source-Free Domain Adaptation Methods

  • Mar 27, 2025
  • Frontiers in Computing and Intelligent Systems
  • Zhiyi Miao
  • PDF
  • Research Article
  • Citations47

Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks.

  • Jan 01, 2022
  • IEEE Transactions on Neural Systems and Rehabilitation Engineering
  • Jiahao Fan +8
  • Conference Article
  • Citations38

Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation

  • Oct 17, 2021
  • Mucong Ye +3
  • Research Article

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

  • Apr 22, 2025
  • Complex & Intelligent Systems
  • Zhirui Wang +2
  • PDF
  • Research Article
  • Citations47

Universal Domain Adaptation for Remote Sensing Image Scene Classification

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Qingsong Xu +3
  • Conference Article
  • Citations9

Universal Domain Adaptation without Source Data for Remote Sensing Image Scene Classification

  • Jul 17, 2022
  • Qingsong Xu +2
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Research Article
  • Citations96

VDM-DA: Virtual Domain Modeling for Source Data-Free Domain Adaptation

  • Jun 01, 2022
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Jiayi Tian +3
  • Conference Article
  • Citations7

Self-Supervised Pre-training on the Target Domain for Cross-Domain Person Re-identification

  • Oct 17, 2021
  • Junyin Zhang +4
  • Research Article
  • Citations138

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Xianfeng Li +6
  • Research Article
  • Citations175

Domain Adaptation Without Source Data

  • Dec 01, 2021
  • IEEE Transactions on Artificial Intelligence
  • Youngeun Kim +4
  • Research Article

Fault diagnosis of rolling bearing with variable working conditions in noisy environment based on dynamic soft threshold and attention mechanism

  • Dec 19, 2024
  • Measurement Science and Technology
  • Ankang Li +3
  • Conference Article
  • Citations3

Modeling Sequential Domain Shift through Estimation of Optimal Sub-spaces for Categorization

  • Jan 01, 2014
  • Suranjana Samanta +2
  • Supplementary Content

On Transfer Learning Techniques for Machine Learning

  • Apr 30, 2020
  • Figshare
  • Debasmit Das
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.