Repeatability Is Not Enough: Learning Affine Regions Via Discriminability

Abstract

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

Stats

• citations169
• S2 citations—
• github stars278
• HF likes0
• heat score21.62
• arxiv keymishkin2017repeatability

Code

• ducha-aiki/affnet—

Related papers

• Working Hard To Know Your Neighbor's Margins: Local Descriptor Learning Loss (2017)0.00
• Descriptor Distillation: A Teacher-student-regularized Framework For Learning Local Descriptors (2022)5.24
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Robust Angular Local Descriptor Learning (2019)3.58
• Learning Geodesic-aware Local Features From RGB-D Images (2022)6.34
• Learning And Aggregating Deep Local Descriptors For Instance-level Recognition (2020)13.88
• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
• Hynet: Learning Local Descriptor With Hybrid Similarity Measure And Triplet Loss (2020)0.00