An accurate retrieval through R-MAC+ descriptors for landmark recognition

06/22/2018
by   Federico Magliani, et al.
0

The landmark recognition problem is far from being solved, but with the use of features extracted from intermediate layers of Convolutional Neural Networks (CNNs), excellent results have been obtained. In this work, we propose some improvements on the creation of R-MAC descriptors in order to make the newly-proposed R-MAC+ descriptors more representative than the previous ones. However, the main contribution of this paper is a novel retrieval technique, that exploits the fine representativeness of the MAC descriptors of the database images. Using this descriptors called "db regions" during the retrieval stage, the performance is greatly improved. The proposed method is tested on different public datasets: Oxford5k, Paris6k and Holidays. It outperforms the state-of-the- art results on Holidays and reached excellent results on Oxford5k and Paris6k, overcame only by approaches based on fine-tuning strategies.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/18/2017

Pruning Convolutional Neural Networks for Image Instance Retrieval

In this work, we focus on the problem of image instance retrieval with d...
research
06/15/2018

Efficient Nearest Neighbors Search for Large-Scale Landmark Recognition

The problem of landmark recognition has achieved excellent results in sm...
research
11/03/2017

Fine-tuning CNN Image Retrieval with No Human Annotation

Image descriptors based on activations of Convolutional Neural Networks ...
research
11/01/2018

Attention-aware Generalized Mean Pooling for Image Retrieval

It has been shown that image descriptors extracted by convolutional neur...
research
01/09/2016

Group Invariant Deep Representations for Image Instance Retrieval

Most image instance retrieval pipelines are based on comparison of vecto...
research
08/15/2016

Visual place recognition using landmark distribution descriptors

Recent work by Suenderhauf et al. [1] demonstrated improved visual place...
research
01/09/2023

Machining feature recognition using descriptors with range constraints for mechanical 3D models

In machining feature recognition, geometric elements generated in a thre...

Please sign up or login with your details

Forgot password? Click here to reset