Detect unknown and known objects using CLIP to generate feature embeddings and proposals with He
Detect unknown and known objects using CLIP to generate feature embeddings and proposals with He
Incremental Object Detection with CLIP
arXiv paper abstract https://arxiv.org/abs/2310.08815
arXiv PDF paper https://arxiv.org/pdf/2310.08815.pdf
In the incremental detection task, unlike the incremental classification task, data ambiguity exists due to the possibility of an image having different labeled bounding boxes in multiple continuous learning stages.
… propose to use a language-visual model such as CLIP to generate text feature embeddings for different class sets, which enhances the feature space globally.
… then employ the broad classes to replace the unavailable novel classes in the early learning stage to simulate the actual incremental scenario.
… use the CLIP image encoder to identify potential objects in the proposals, which are classified into the background by the model.
… modify the background labels of those proposals to known classes and add the boxes to the training set to alleviate the problem of data ambiguity.
… approach outperforms state-of-the-art methods, particularly for the new classes.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
