Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Bags of local convolutional features for scalable instance search

Mohedano, Eva, Salvador, Amaia, McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477, Giró-i-Nieto, Xavier orcid logoORCID: 0000-0002-9935-5332, O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 and Marqués, Ferran (2016) Bags of local convolutional features for scalable instance search. In: ICMIR 2016, 3-6 June 2016, New York, NY..

Abstract
This work proposes a simple instance retrieval pipeline based on encoding the convolutional features of CNN using the bag of words aggregation scheme (BoW). Assigning each local array of activations in a convolutional layer to a visual word produces an assignment map, a compact representation that relates regions of an image with a visual word. We use the assignment map for fast spatial reranking, obtain- ing object localizations that are used for query expansion. We demonstrate the suitability of the BoW representation based on local CNN features for instance retrieval, achieving competitive performance on the Oxford and Paris buildings benchmarks. We show that our proposed system for CNN feature aggregation with BoW outperforms state-of-the-art techniques using sum pooling at a subset of the challenging TRECVid INS benchmark.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:No
Subjects:Computer Science > Machine learning
Computer Science > Image processing
Computer Science > Information retrieval
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:SFI/12/RC/2289, BigGraph TEC2013-43935-R, GeForce GTX Titan X from NVIDIA Corporation
ID Code:21175
Deposited On:22 Jun 2016 10:20 by Eva Mohedano Robles . Last Modified 06 Nov 2019 14:26
Documents

Full text available as:

[thumbnail of short paper]
Preview
PDF (short paper) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
3MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record