Detect object with few examples by generating synthetic variations from the base dataset with SFOT
Few-Shot Object Detection via Synthetic Features with Optimal Transport
arXiv paper abstract https://arxiv.org/abs/2308.15005
arXiv PDF paper https://arxiv.org/pdf/2308.15005.pdf
Few-shot object detection aims to simultaneously localize and classify the objects in an image with limited training samples.
However, most existing few-shot object detection methods focus on extracting the features of a few samples of novel classes that lack diversity.
... propose a novel approach in which ... train a generator to generate synthetic data for novel classes
... goal is to train a generator that captures the data variations of the base dataset ... then transform the captured variations into novel classes by generating synthetic data with the trained generator.
To encourage the generator to capture data variations on base classes, ... train the generator with an optimal transport loss that minimizes the optimal transport distance between the distributions of real and synthetic data.
Extensive experiments on two benchmark datasets demonstrate that the proposed method outperforms the state of the art ...
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