Better object detection with few examples by get characteristics regardless of class with hANMCL
Better object detection with few examples by get characteristics regardless of class with hANMCL
Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning
arXiv paper abstract https://arxiv.org/abs/2208.07039
arXiv PDF paper https://arxiv.org/pdf/2208.07039.pdf
Few-shot object detection (FSOD) aims to classify and detect few images of novel categories.
Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations.
... propose a hierarchical attention network with sequentially large receptive fields to fully exploit the query and support images.
... meta-learning does not distinguish the categories well because it determines whether the support and query images match ... is ineffective because it does not work directly.
... propose a contrastive learning method called meta-contrastive learning, which directly helps achieve the purpose of the meta-learning strategy.
... establish a new state-of-the-art network, by realizing significant margins
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