Object detection using one example by using scale and features with SaFT
Object detection using one example by using scale and features with SaFT
Semantic-aligned Fusion Transformer for One-shot Object Detection
arXiv paper abstract https://arxiv.org/abs/2203.09093
arXiv PDF paper https://arxiv.org/pdf/2203.09093.pdf
One-shot object detection aims at detecting novel objects according to merely one given instance.
... leverage the attention mechanism and propose ... Semantic-aligned Fusion Transformer (SaFT) ... with a vertical fusion module (VFM) for cross-scale semantic enhancement and a horizontal fusion module (HFM) for cross-sample feature fusion.
Together, they broaden the vision for each feature point from the support to a whole augmented feature pyramid from the query, facilitating semantic-aligned associations.
Extensive experiments on multiple benchmarks demonstrate the superiority of ... framework.
Without fine-tuning on novel classes, it brings significant performance gains to one-stage baselines, lifting state-of-the-art results to a higher level.
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