2017/11/17 by Dmytro Mishkin, Filip Radenović, Mishkin, Dmytro +5 · 5 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Image Retrieval and Classification Techniques #Neural and Evolutionary Computing (cs.NE) #cs.CV #cs.NE
paper · pdf · doi:10.48550/arxiv.1711.06704
ECCV 2018 camera ready
openalex publication_date 2017/11/17 · arxiv created 2018/08/28 · arxiv updated 2018/08/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
A method for learning local affine-covariant regions is presented. We show that maximizing geometric repeatability does not lead to local regions, a.k.a features,that are reliably matched and this necessitates descriptor-based learning. We explore factors that influence such learning and registration: the loss function, descriptor type, geometric parametrization and the trade-off between matchability and geometric accuracy and propose a novel hard negative-constant loss function for learning of affine regions. The affine shape estimator -- AffNet -- trained with the hard negative-constant loss outperforms the state-of-the-art in bag-of-words image retrieval and wide baseline stereo. The proposed training process does not require precisely geometrically aligned patches.The source codes and trained weights are available at https://github.com/ducha-aiki/affnet