Local Feature Descriptor Learning With Adaptive Siamese Network

Abstract

Although the recent progress in the deep neural network has led to the development of learnable local feature descriptors, there is no explicit answer for estimation of the necessary size of a neural network. Specifically, the local feature is represented in a low dimensional space, so the neural network should have more compact structure. The small networks required for local feature descriptor learning may be sensitive to initial conditions and learning parameters and more likely to become trapped in local minima. In order to address the above problem, we introduce an adaptive pruning Siamese Architecture based on neuron activation to learn local feature descriptors, making the network more computationally efficient with an improved recognition rate over more complex networks. Our experiments demonstrate that our learned local feature descriptors outperform the state-of-art methods in patch matching.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuang2017local

Related papers

• Working Hard To Know Your Neighbor's Margins: Local Descriptor Learning Loss (2017)0.00
• Semi-supervised Learning Using Siamese Networks (2021)7.50
• Learning And Aggregating Deep Local Descriptors For Instance-level Recognition (2020)13.88
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Content-based Landmark Retrieval Combining Global And Local Features Using Siamese Neural Networks (2022)0.00
• Local Feature Matching Using Deep Learning: A Survey (2024)18.68
• Learning-based Dimensionality Reduction For Computing Compact And Effective Local Feature Descriptors (2022)9.99
• DH3D: Deep Hierarchical 3D Descriptors For Robust Large-scale 6dof Relocalization (2020)14.76