Descriptor Distillation: A Teacher-student-regularized Framework For Learning Local Descriptors

Abstract

Learning a fast and discriminative patch descriptor is a challenging topic in computer vision. Recently, many existing works focus on training various descriptor learning networks by minimizing a triplet loss (or its variants), which is expected to decrease the distance between each positive pair and increase the distance between each negative pair. However, such an expectation has to be lowered due to the non-perfect convergence of network optimizer to a local solution. Addressing this problem and the open computational speed problem, we propose a Descriptor Distillation framework for local descriptor learning, called DesDis, where a student model gains knowledge from a pre-trained teacher model, and it is further enhanced via a designed teacher-student regularizer. This teacher-student regularizer is to constrain the difference between the positive (also negative) pair similarity from the teacher model and that from the student model, and we theoretically prove that a more effective

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyliu2022descriptor

Related papers

• Working Hard To Know Your Neighbor's Margins: Local Descriptor Learning Loss (2017)0.00
• Learning And Aggregating Deep Local Descriptors For Instance-level Recognition (2020)13.88
• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
• Repeatability Is Not Enough: Learning Affine Regions Via Discriminability (2017)21.62
• Context Unaware Knowledge Distillation For Image Retrieval (2022)0.60
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Data-efficient Ranking Distillation For Image Retrieval (2020)0.00
• Robust Angular Local Descriptor Learning (2019)3.58