Image Retrieval Using Multi-scale CNN Features Pooling

Abstract

In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on NetVLAD and a triplet mining procedure based on samples difficulty to obtain an effective image representation. Extensive experiments show that our approach is able to reach state-of-the-art results on three standard datasets.

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keyvaccaro2020image

Related papers

• REMAP: Multi-layer Entropy-guided Pooling Of Dense CNN Features For Image Retrieval (2019)12.33
• ACTNET: End-to-end Learning Of Feature Activations And Multi-stream Aggregation For Effective Instance Image Retrieval (2019)10.07
• From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
• Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
• What Is The Best Practice For Cnns Applied To Visual Instance Retrieval? (2016)0.00
• A Fast Content-based Image Retrieval Method Using Deep Visual Features (2019)6.77
• Image Retrieval Method Based On CNN And Dimension Reduction (2019)5.24
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67