Improve object detection using object co-occurrence statistics with GPR
Improve object detection using object co-occurrence statistics with GPR
Detecting Objects with Graph Priors and Graph Refinement
arXiv paper abstract https://arxiv.org/abs/2212.12395
arXiv PDF paper https://arxiv.org/pdf/2212.12395.pdf
… goal … is to detect objects by exploiting their interrelationships.
Rather than relying on predefined and labeled graph structures, … infer a graph prior from object co-occurrence statistics.
… idea … is to model object relations as a function of initial class predictions and co-occurrence priors to generate a graph representation of an image for improved classification and bounding box regression.
… additionally learn the object-relation joint distribution … Sampling from this distribution generates a refined graph representation of the image which in turn produces improved detection performance.
… demonstrate … method is detector agnostic, end-to-end trainable, and especially beneficial for rare object classes.
… establish a consistent improvement over object detectors like DETR and Faster-RCNN, as well as state-of-the-art methods modeling object interrelationships.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
