University of Surrey

Test tubes in the lab Research in the ATI Dance Research

REMAP: Multi-layer entropy-guided pooling of dense CNN features for image retrieval

Husain, Syed Sameed and Bober, Miroslaw (2019) REMAP: Multi-layer entropy-guided pooling of dense CNN features for image retrieval IEEE Transactions on Image Processing.

REMAP_IEEE_TIP.pdf - Accepted version Manuscript

Download (5MB) | Preview


This paper addresses the problem of very large-scale image retrieval, focusing on improving its accuracy and robustness. We target enhanced robustness of search to factors such as variations in illumination, object appearance and scale, partial occlusions, and cluttered backgrounds -particularly important when search is performed across very large datasets with significant variability. We propose a novel CNN-based global descriptor, called REMAP, which learns and aggregates a hierarchy of deep features from multiple CNN layers, and is trained end-to-end with a triplet loss. REMAP explicitly learns discriminative features which are mutually-supportive and complementary at various semantic levels of visual abstraction. These dense local features are max-pooled spatially at each layer, within multi-scale overlapping regions, before aggregation into a single image-level descriptor. To identify the semantically useful regions and layers for retrieval, we propose to measure the information gain of each region and layer using KL-divergence. Our system effectively learns during training how useful various regions and layers are and weights them accordingly. We show that such relative entropy-guided aggregation outperforms classical CNN-based aggregation controlled by SGD. The entire framework is trained in an end-to-end fashion, outperforming the latest state-of-the-art results. On image retrieval datasets Holidays, Oxford and MPEG, the REMAP descriptor achieves mAP of 95.5%, 91.5% and 80.1% respectively, outperforming any results published to date. REMAP also formed the core of the winning submission to the Google Landmark Retrieval Challenge on Kaggle.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences
Authors :
Husain, Syed
Date : 22 May 2019
Funders : Engineering and Physical Sciences Research Council (EPSRC), Defence, Science and Technology Laboratory (DSTL)
DOI : 10.1109/TIP.2019.2917234
Grant Title : iTravel - A Virtual Journey Assistant
Copyright Disclaimer : © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Uncontrolled Keywords : Global image descriptor; Object recognition; Instance retrieval; CNN; Deep features; KL-divergence; Feature extraction; Computer architecture; Training; Entropy; Image retrieval; Visualization; Aggregates
Depositing User : Clive Harris
Date Deposited : 19 Jun 2019 08:19
Last Modified : 19 Jul 2019 08:08

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800