Computer Vision and Pattern Recognition 2017

Learning discriminative and transformation covariant local feature detectors.

Computer Vision and Pattern Recognition 2017 ColumbiaDVMM/Transform_Covariant_Detector

Specifically, we extend the covariant constraint proposed by Lenc and Vedaldi [8] by defining the concepts of “standard patch” and “canonical feature” and leverage these to train a novel robust covariant detector.

IMAGE RETRIEVAL