Learning And Aggregating Deep Local Descriptors For Instance-level Recognition

Abstract

We propose an efficient method to learn deep local descriptors for instance-level recognition. The training only requires examples of positive and negative image pairs and is performed as metric learning of sum-pooled global image descriptors. At inference, the local descriptors are provided by the activations of internal components of the network. We demonstrate why such an approach learns local descriptors that work well for image similarity estimation with classical efficient match kernel methods. The experimental validation studies the trade-off between performance and memory requirements of the state-of-the-art image search approach based on match kernels. Compared to existing local descriptors, the proposed ones perform better in two instance-level recognition tasks and keep memory requirements lower. We experimentally show that global descriptors are not effective enough at large scale and that local descriptors are essential. We achieve state-of-the-art performance, in some cas

Stats

• citations70
• S2 citations—
• github stars0
• HF likes0
• heat score13.88
• arxiv keytolias2020learning

Related papers

• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• 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
• Local Features And Visual Words Emerge In Activations (2019)13.55
• Aggregating Binary Local Descriptors For Image Retrieval (2016)7.16
• Hpatches: A Benchmark And Evaluation Of Handcrafted And Learned Local Descriptors (2017)11.08
• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59