Sosnet: Second Order Similarity Regularization For Local Descriptor Learning

Abstract

Despite the fact that Second Order Similarity (SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors. In this work, we explore the potential of SOS in the field of descriptor learning by building upon the intuition that a positive pair of matching points should exhibit similar distances with respect to other points in the embedding space. Thus, we propose a novel regularization term, named Second Order Similarity Regularization (SOSR), that follows this principle. By incorporating SOSR into training, our learned descriptor achieves state-of-the-art performance on several challenging benchmarks containing distinct tasks ranging from local patch retrieval to structure from motion. Furthermore, by designing a von Mises-Fischer distribution based evaluation method, we link the utilization of the descriptor space to the matching performance, thus demonstrating the effectiveness of our proposed SOS

Stats

• citations310
• S2 citations—
• github stars0
• HF likes0
• heat score18.70
• arxiv keytian2019sosnet

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
• SOLAR: Second-order Loss And Attention For Image Retrieval (2020)18.69
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Hynet: Learning Local Descriptor With Hybrid Similarity Measure And Triplet Loss (2020)0.00
• Descriptor Distillation: A Teacher-student-regularized Framework For Learning Local Descriptors (2022)5.24
• Metric Learning With HORDE: High-order Regularizer For Deep Embeddings (2019)12.81
• Learning And Aggregating Deep Local Descriptors For Instance-level Recognition (2020)13.88