Siamese Network Of Deep Fisher-vector Descriptors For Image Retrieval

Abstract

This paper addresses the problem of large scale image retrieval, with the aim of accurately ranking the similarity of a large number of images to a given query image. To achieve this, we propose a novel Siamese network. This network consists of two computational strands, each comprising of a CNN component followed by a Fisher vector component. The CNN component produces dense, deep convolutional descriptors that are then aggregated by the Fisher Vector method. Crucially, we propose to simultaneously learn both the CNN filter weights and Fisher Vector model parameters. This allows us to account for the evolving distribution of deep descriptors over the course of the learning process. We show that the proposed approach gives significant improvements over the state-of-the-art methods on the Oxford and Paris image retrieval datasets. Additionally, we provide a baseline performance measure for both these datasets with the inclusion of 1 million distractors.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyong2017siamese

Related papers

• Group Invariant Deep Representations For Image Instance Retrieval (2016)0.00
• Retrieving Similar E-commerce Images Using Deep Learning (2019)0.00
• Coarse2fine: Two-layer Fusion For Image Retrieval (2016)0.00
• Retrieval Of Family Members Using Siamese Neural Network (2020)7.81
• Image Retrieval And Pattern Spotting Using Siamese Neural Network (2019)11.58
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• A Fast Content-based Image Retrieval Method Using Deep Visual Features (2019)6.77
• REMAP: Multi-layer Entropy-guided Pooling Of Dense CNN Features For Image Retrieval (2019)12.33