Hierarchical Metric Learning And Matching For 2D And 3D Geometric Correspondences

Abstract

Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We demonstrate that commonly used metric learning approaches do not optimally leverage the feature hierarchies learned in a Convolutional Neural Network (CNN), especially when applied to the task of geometric feature matching. While a metric loss applied to the deepest layer of a CNN, is often expected to yield ideal features irrespective of the task, in fact the growing receptive field as well as striding effects cause shallower features to be better at high precision matching tasks. We leverage this insight together with explicit supervision at multiple levels of the feature hierarchy for better regularization, to learn more effective descriptors in the context of geometric matching tasks. Further, we propose to use activation maps at different layer

Stats

• citations32
• S2 citations—
• github stars0
• HF likes0
• heat score11.39
• arxiv keyfathy2018hierarchical

Related papers

• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
• Towards Interpretable Deep Metric Learning With Structural Matching (2021)15.87
• End-to-end Learning Of Keypoint Detector And Descriptor For Pose Invariant 3D Matching (2018)12.40
• Multi-scale Convolutions For Learning Context Aware Feature Representations (2019)0.00
• Improving The Matching Of Deformable Objects By Learning To Detect Keypoints (2023)7.74
• Geometric Image Correspondence Verification By Dense Pixel Matching (2019)7.16
• LCD: Learned Cross-domain Descriptors For 2D-3D Matching (2019)13.74
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77