Detect object with few examples using transformer to explore useful contextual fields with SCT
Detect object with few examples using transformer to explore useful contextual fields with SCT
Few-Shot Object Detection with Sparse Context Transformers
arXiv paper abstract https://arxiv.org/abs/2402.09315
arXiv PDF paper https://arxiv.org/pdf/2402.09315.pdf
Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data.
One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection model in a source domain prior to its fine-tuning in a target domain.
However, it is challenging for fine-tuned models to effectively identify new classes in the target domain, particularly when the underlying labeled training data are scarce.
… devise a … sparse context transformer (SCT) that … leverages object knowledge in the source domain, and … learns a sparse context from only few training images in the target domain.
As a result, it combines different relevant clues in order to enhance the discrimination power of the learned detectors and reduce class confusion.
… proposed method obtains competitive performance compared to the related state-of-the-art.
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
