Few-shot Object Detection via Feature Reweighting
International Conference on Computer Vision, Volume abs/1812.01866, 2018, Pages 8420-8429.
This work aims to solve the challenging few-shot object detection problem where only a few annotated examples are available for each object category to train a detection model. Such an ability of learning to detect an object from just a few examples is common for human vision systems, but remains absent for computer vision systems. Though...More
PPT (Upload PPT)