Improved object detection when test and train domains differ with MS-DAYOLO
Improved object detection when test and train domains differ with MS-DAYOLO
Integrated Multiscale Domain Adaptive YOLO
arXiv paper abstract https://arxiv.org/abs/2202.03527v2
arXiv PDF paper https://arxiv.org/pdf/2202.03527v2.pdf
... domain shift problem ... arises due to the difference between the distributions of source data used for training in comparison with target data used during realistic testing
... introduce a novel MultiScale Domain Adaptive YOLO (MS-DAYOLO) framework that employs multiple domain adaptation paths and ... domain classifiers at different scales of ... YOLOv4
... introduce ... Domain Adaptation Network (DAN) that generates domain-invariant features ... propose a Progressive Feature Reduction (PFR), a Unified Classifier (UC), and an Integrated architecture.
... show significant improvements in object detection ... when training YOLOv4 using ... MS-DAYOLO ... and when tested on target data for autonomous driving applications.
... MS-DAYOLO ... achieves an order of magnitude real-time speed improvement relative to Faster R-CNN solutions while providing comparable object detection performance.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments