Source data-free domain adaptation for a faster R-CNN
Authors:
- Lin XiongLXLin Xiong
- Mao YeMYMao Ye
- Dan ZhangDZDan Zhang
- Yan GanYGYan Gan
- Yiguang LiuYLYiguang Liu
- 1 April 2022
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 124
Abstract
No abstract availableKeywords
This publication has 17 references indexed in Scilit:
- Focal Loss for Dense Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Mask R-CNNIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Semantic Foggy Scene Understanding with Synthetic DataInternational Journal of Computer Vision, 2018
- Semi-supervised transfer subspace for domain adaptationPattern Recognition, 2018
- Adaptive Deep Convolutional Neural Networks for Scene-Specific Object DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2017
- Accurate object detection using memory-based models in surveillance scenesPattern Recognition, 2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- A theory of learning from different domainsMachine Learning, 2009
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009