Detect known objects and group similar unknown objects with ORCA
Detect known objects and group similar unknown objects with ORCA
Open-World Semi-Supervised Learning
arXiv paper abstract https://arxiv.org/abs/2102.03526
arXiv PDF paper https://arxiv.org/pdf/2102.03526.pdf
A fundamental limitation of applying semi-supervised learning in real-world settings is the assumption that unlabeled test data contains only classes previously encountered in the labeled training data.
... assumption rarely holds for data in-the-wild, where instances belonging to novel classes may appear at testing time.
... introduce a novel open-world semi-supervised learning setting ... that novel classes may appear in the unlabeled test data.
... goal is to solve the class distribution mismatch between labeled and unlabeled data, where ... every input instance either needs to be classified into one of the existing classes or a new unseen class needs to be initialized.
... propose ORCA, ... introduces uncertainty adaptive margin mechanism to circumvent the bias towards seen classes caused by learning discriminative features for seen classes faster than for the novel classes.
... dataset demonstrate that ORCA consistently outperforms alternative baselines, achieving 25% improvement on seen and 96% improvement on novel classes of the ImageNet dataset.
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