Visual Instance Retrieval with Deep Convolutional Networks

Abstract

This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we present an efficient pipeline exploiting multi-scale schemes to extract local features, in particular, by taking geometric invariance into explicit account, i.e. positions, scales and spatial consistency. In our experiments using five standard image retrieval datasets, we demonstrate that generic ConvNet image representations can outperform other state-of-the-art methods if they are extracted appropriately.

Cited by in corpus (7)

• PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval
• Attention-based Pyramid Aggregation Network for Visual Place Recognition
• Investigating the Role of Image Retrieval for Visual Localization -- An exhaustive benchmark
• Relative Camera Pose Estimation Using Convolutional Neural Networks
• Local Feature Detectors, Descriptors, and Image Representations: A Survey
• MILDNet: A Lightweight Single Scaled Deep Ranking Architecture
• Improving Nighttime Retrieval-Based Localization