Hynet: Learning Local Descriptor With Hybrid Similarity Measure And Triplet Loss

Abstract

Recent works show that local descriptor learning benefits from the use of L2 normalisation, however, an in-depth analysis of this effect lacks in the literature. In this paper, we investigate how L2 normalisation affects the back-propagated descriptor gradients during training. Based on our observations, we propose HyNet, a new local descriptor that leads to state-of-the-art results in matching. HyNet introduces a hybrid similarity measure for triplet margin loss, a regularisation term constraining the descriptor norm, and a new network architecture that performs L2 normalisation of all intermediate feature maps and the output descriptors. HyNet surpasses previous methods by a significant margin on standard benchmarks that include patch matching, verification, and retrieval, as well as outperforming full end-to-end methods on 3D reconstruction tasks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytian2020hynet

Related papers

• Working Hard To Know Your Neighbor's Margins: Local Descriptor Learning Loss (2017)0.00
• Robust Angular Local Descriptor Learning (2019)3.58
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Tcdesc: Learning Topology Consistent Descriptors (2020)0.00
• Sdgmnet: Statistic-based Dynamic Gradient Modulation For Local Descriptor Learning (2021)2.26
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Hpatches: A Benchmark And Evaluation Of Handcrafted And Learned Local Descriptors (2017)11.08
• Learning And Aggregating Deep Local Descriptors For Instance-level Recognition (2020)13.88