Object detection with only image labels using weighted ensemble model with WSOD-CBL
Object detection with only image labels using weighted ensemble model with WSOD-CBL
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
arXiv paper abstract https://arxiv.org/abs/2308.05991
arXiv PDF paper https://arxiv.org/pdf/2308.05991.pdf
Recent progress in weakly supervised object detection is featured by a combination of multiple instance detection networks (MIDN) and ordinal online refinement ... explore how to ameliorate the quality of pseudo-labeling in MIDN.
... devise Cyclic-Bootstrap Labeling (CBL), a novel weakly supervised object detection pipeline, which optimizes MIDN with rank information from a reliable teacher network.
... obtain this teacher network by introducing a weighted exponential moving average strategy to take advantage of various refinement modules.
A novel class-specific ranking distillation algorithm is proposed to leverage the output of weighted ensembled teacher network for distilling MIDN with rank information.
As a result, MIDN is guided to assign higher scores to accurate proposals among their neighboring ones, thus benefiting the subsequent pseudo labeling.
.. demonstrate the superior performance of ... CBL framework ...
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