Sdgmnet: Statistic-based Dynamic Gradient Modulation For Local Descriptor Learning

Abstract

Modifications on triplet loss that rescale the back-propagated gradients of special pairs have made significant progress on local descriptor learning. However, current gradient modulation strategies are mainly static so that they would suffer from changes of training phases or datasets. In this paper, we propose a dynamic gradient modulation, named SDGMNet, to improve triplet loss for local descriptor learning. The core of our method is formulating modulation functions with statistical characteristics which are estimated dynamically. Firstly, we perform deep analysis on back propagation of general triplet-based loss and introduce included angle for distance measure. On this basis, auto-focus modulation is employed to moderate the impact of statistically uncommon individual pairs in stochastic gradient descent optimization; probabilistic margin cuts off the gradients of proportional Siamese pairs that are believed to reach the optimum; power adjustment balances the total weights of nega

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyma2021sdgmnet

Related papers

• Hynet: Learning Local Descriptor With Hybrid Similarity Measure And Triplet Loss (2020)0.00
• Robust Angular Local Descriptor Learning (2019)3.58
• 3D Object Instance Recognition And Pose Estimation Using Triplet Loss With Dynamic Margin (2019)11.76
• Tcdesc: Learning Topology Consistent Descriptors (2020)0.00
• Working Hard To Know Your Neighbor's Margins: Local Descriptor Learning Loss (2017)0.00
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77
• Descriptor Distillation: A Teacher-student-regularized Framework For Learning Local Descriptors (2022)5.24