Tcdesc: Learning Topology Consistent Descriptors

Abstract

Triplet loss is widely used for learning local descriptors from image patch. However, triplet loss only minimizes the Euclidean distance between matching descriptors and maximizes that between the non-matching descriptors, which neglects the topology similarity between two descriptor sets. In this paper, we propose topology measure besides Euclidean distance to learn topology consistent descriptors by considering kNN descriptors of positive sample. First we establish a novel topology vector for each descriptor followed by Locally Linear Embedding (LLE) to indicate the topological relation among the descriptor and its kNN descriptors. Then we define topology distance between descriptors as the difference of their topology vectors. Last we employ the dynamic weighting strategy to fuse Euclidean distance and topology distance of matching descriptors and take the fusion result as the positive sample distance in the triplet loss. Experimental results on several benchmarks show that our meth

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypan2020tcdesc

Related papers

• Hynet: Learning Local Descriptor With Hybrid Similarity Measure And Triplet Loss (2020)0.00
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Deep Metric Learning With Hierarchical Triplet Loss (2018)18.20
• Neighborhood Watch: Representation Learning With Local-margin Triplet Loss And Sampling Strategy For K-nearest-neighbor Image Classification (2019)0.00
• Triplet-center Loss For Multi-view 3D Object Retrieval (2018)18.70
• Robust Angular Local Descriptor Learning (2019)3.58
• Working Hard To Know Your Neighbor's Margins: Local Descriptor Learning Loss (2017)0.00
• Sdgmnet: Statistic-based Dynamic Gradient Modulation For Local Descriptor Learning (2021)2.26