Better object detection with few examples by spatial reasoning on known objects with FSOD-SR
Better object detection with few examples by spatial reasoning on known objects with FSOD-SR
Spatial Reasoning for Few-Shot Object Detection
arXiv paper abstract https://arxiv.org/abs/2211.01080
arXiv PDF paper https://arxiv.org/pdf/2211.01080.pdf
Although modern object detectors rely heavily on a significant amount of training data, humans can easily detect novel objects using a few training examples.
The mechanism of the human visual system is to interpret spatial relationships among various objects and this process enables us to exploit contextual information by considering the co-occurrence of objects.
... propose a spatial reasoning framework that detects novel objects with only a few training examples in a context.
... infer geometric relatedness between novel and base RoIs (Region-of-Interests) to enhance the feature representation of novel categories using an object detector well trained on base categories.
... employ a graph convolutional network as the RoIs and their relatedness are defined as nodes and edges, respectively.
... demonstrate that the proposed method significantly outperforms the state-of-the-art methods ...
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