Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval

Abstract: 

One of the key challenges of deep learning based image retrieval remains in aggregating convolutional activations into one highly representative feature vector. Ideally, this descriptor should encode semantic, spatial and low level information. Even though off-the-shelf pre-trained neural networks can already produce good representations in combination with aggregation methods, appropriate fine tuning for the task of image retrieval has shown to significantly boost retrieval performance. In this paper, we present a simple yet effective supervised aggregation method built on top of existing regional pooling approaches. In addition to the maximum activation of a given region, we calculate regional average activations of extracted feature maps. Subsequently, weights for each of the pooled feature vectors are learned to perform a weighted aggregation to a single feature vector. Furthermore, we apply our newly proposed NRA loss function for deep metric learning to fine tune the backbone neural network and to learn the aggregation weights. Our method achieves state-of-the-art results for the INRIA Holidays data set and competitive results for the Oxford Buildings and Paris data sets while reducing the training time significantly.

up
0 users have voted:

Paper Details

Authors:
Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung
Submitted On:
25 September 2019 - 8:15am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Konstantin Schall
Paper Code:
6068345
Document Year:
2019
Cite

Document Files

MMSP19_DARAC.pdf

(19)

Subscribe

[1] Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung, "Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4840. Accessed: Dec. 13, 2019.
@article{4840-19,
url = {http://sigport.org/4840},
author = {Konstantin Schall; Kai Uwe Barthel; Nico Hezel; Klaus Jung },
publisher = {IEEE SigPort},
title = {Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval},
year = {2019} }
TY - EJOUR
T1 - Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval
AU - Konstantin Schall; Kai Uwe Barthel; Nico Hezel; Klaus Jung
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4840
ER -
Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung. (2019). Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval. IEEE SigPort. http://sigport.org/4840
Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung, 2019. Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval. Available at: http://sigport.org/4840.
Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung. (2019). "Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval." Web.
1. Konstantin Schall, Kai Uwe Barthel, Nico Hezel, Klaus Jung. Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4840