Robust Angular Local Descriptor Learning

Abstract

In recent years, the learned local descriptors have outperformed handcrafted ones by a large margin, due to the powerful deep convolutional neural network architectures such as L2-Net [1] and triplet based metric learning [2]. However, there are two problems in the current methods, which hinders the overall performance. Firstly, the widely-used margin loss is sensitive to incorrect correspondences, which are prevalent in the existing local descriptor learning datasets. Second, the L2 distance ignores the fact that the feature vectors have been normalized to unit norm. To tackle these two problems and further boost the performance, we propose a robust angular loss which 1) uses cosine similarity instead of L2 distance to compare descriptors and 2) relies on a robust loss function that gives smaller penalty to triplets with negative relative similarity. The resulting descriptor shows robustness on different datasets, reaching the state-of-the-art result on Brown dataset , as well as demo

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyxu2019robust

Related papers

• Working Hard To Know Your Neighbor's Margins: Local Descriptor Learning Loss (2017)0.00
• Hynet: Learning Local Descriptor With Hybrid Similarity Measure And Triplet Loss (2020)0.00
• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Sosnet: Second Order Similarity Regularization For Local Descriptor Learning (2019)18.70
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Sdgmnet: Statistic-based Dynamic Gradient Modulation For Local Descriptor Learning (2021)2.26
• LCD: Learned Cross-domain Descriptors For 2D-3D Matching (2019)13.74