research-article

Fully Unsupervised Convolutional Learning for Fast Image Retrieval

Authors:

Anastasios TefasAuthors Info & Claims

SETN '18: Proceedings of the 10th Hellenic Conference on Artificial Intelligence

Article No.: 1, Pages 1 - 6

https://doi.org/10.1145/3200947.3201007

Published: 09 July 2018 Publication History

Abstract

In this paper, we propose a fully unsupervised method for optimizing the Convolutional Neural Network (CNN) representations towards image retrieval. To accomplish this goal, we obtain the feature representations from the activations of the convolutional layers of a CNN pretrained model, and then we adapt it to a lightweight fully convolutional network, which allows for producing compact image representations, reducing the storage requirements. Subsequently, we retrain the weights of the convolutional layers in order to produce more efficient compact image descriptors, which improve the retrieval performance both in terms of time and precision, in a fully unsupervised fashion. The experimental evaluation on three publicly available image retrieval datasets indicates the effectiveness of the proposed method in learning more efficient representations for the retrieval task, outperforming other unsu-pervised CNN-based retrieval techniques, as well as conventional hand-crafted feature-based approaches in all the used datasets.

References

[1]

Ahmad Alzu'bi, Abbes Amira, and Naeem Ramzan. 2017. Content-based image retrieval with compact deep convolutional features. Neurocomputing 249 (2017), 95--105.

Digital Library

[2]

Relja Arandjelovic and Andrew Zisserman. 2013. All about VLAD. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1578--1585.

Digital Library

[3]

Artem Babenko and Victor Lempitsky. 2015. Aggregating local deep features for image retrieval. In Proceedings of the IEEE International Conference on Computer Vision. 1269--1277.

Digital Library

[4]

Artem Babenko, Anton Slesarev, Alexandr Chigorin, and Victor Lempitsky. 2014. Neural codes for image retrieval. In European Conference on Computer Vision (ECCV). Springer, 584--599.

[5]

Ritendra Datta, Jia Li, and James Z Wang. 2005. Content-based image retrieval: approaches and trends of the new age. In Proceedings of the 7th ACM SIGMM international workshop on Multimedia information retrieval. ACM, 253--262.

Digital Library

[6]

Li Deng. 2014. A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Transactions on Signal and Information Processing 3 (2014), e2.

[7]

Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. 2014. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. In ICML. 647--655.

Digital Library

[8]

Yunchao Gong, Liwei Wang, Ruiqi Guo, and Svetlana Lazebnik. 2014. Multi-scale orderless pooling of deep convolutional activation features. In European Conference on Computer Vision (ECCV). Springer, 392--407.

[9]

Albert Gordo, Jon Almazán, Jerome Revaud, and Diane Larlus. 2016. Deep image retrieval: Learning global representations for image search. In European Conference on Computer Vision. Springer, 241--257.

[10]

Yanming Guo, Yu Liu, Ard Oerlemans, Songyang Lao, Song Wu, and Michael S Lew. 2016. Deep learning for visual understanding: A review. Neurocomputing 187 (2016), 27--48.

Digital Library

[11]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision. 1026--1034.

Digital Library

[12]

Hervé Jégou, Florent Perronnin, Matthijs Douze, Javier Sanchez, Pablo Perez, and Cordelia Schmid. 2012. Aggregating local image descriptors into compact codes. IEEE Transactions on Pattern Analysis and Machine Intelligence 34, 9 (2012), 1704--1716.

Digital Library

[13]

Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia. ACM, 675--678.

Digital Library

[14]

Yannis Kalantidis, Clayton Mellina, and Simon Osindero. 2015. Cross-dimensional weighting for aggregated deep convolutional features. In European Conference on Computer Vision (ECCV) Workshops. Springer, 685--701.

[15]

Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).

[16]

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.

Digital Library

[17]

B Boser Le Cun, John S Denker, D Henderson, Richard E Howard, WHubbard, and Lawrence D Jackel. 1990. Handwritten digit recognition with a back-propagation network. In Advances in neural information processing systems 2. Morgan Kaufmann Publishers Inc., 396--404.

Digital Library

[18]

Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In European conference on computer vision. Springer, 21--37.

[19]

Ziqiong Liu, Shengjin Wang, and Qi Tian. 2016. Fine-residual VLAD for image retrieval. Neurocomputing 173 (2016), 1183--1191.

Digital Library

[20]

Jonathan Long, Evan Shelhamer, and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3431--3440.

[21]

Eva Mohedano, Kevin McGuinness, Noel E O'Connor, Amaia Salvador, Ferran Marques, and Xavier Giro-i Nieto. 2016. Bags of Local Convolutional Features for Scalable Instance Search. In Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval. ACM, 327--331.

Digital Library

[22]

Joe Ng, Fan Yang, and Larry Davis. 2015. Exploiting local features from deep networks for image retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 53--61.

[23]

Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y Ng. 2011. Multimodal deep learning. In Proceedings of the 28th International Conference on Machine Learning (ICML). 689--696.

Digital Library

[24]

David Nister and Henrik Stewenius. 2006. Scalable recognition with a vocabulary tree. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2. IEEE, 2161--2168.

Digital Library

[25]

Nikolaos Passalis and Anastasios Tefas. 2016. Spatial bag of features learning for large scale face image retrieval. In INNS Conference on Big Data. Springer, 8--17.

[26]

Florent Perronnin, Yan Liu, Jorge Sánchez, and Hervé Poirier. 2010. Large-scale image retrieval with compressed fisher vectors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3384--3391.

[27]

James Philbin, Ond&rnrej Chum, Michael Isard, Josef Sivic, and Andrew Zisserman. 2008. Lost in quantization: Improving particular object retrieval in large scale image databases. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1--8.

[28]

Ali Razavian, Hossein Azizpour, Josephine Sullivan, and Stefan Carlsson. 2014. CNN features off-the-shelf: an astounding baseline for recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 806--813.

Digital Library

[29]

Joseph Redmon and Ali Farhadi. 2016. YOLO9000: better, faster, stronger. arXiv preprint arXiv:1612.08242 (2016).

[30]

Arnold WM Smeulders, Marcel Worring, Simone Santini, Amarnath Gupta, and Ramesh Jain. 2000. Content-based image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 12 (2000), 1349--1380.

Digital Library

[31]

Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, and Lior Wolf. 2014. Deepface: Closing the gap to human-level performance in face verification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1701--1708.

Digital Library

[32]

Giorgos Tolias, Ronan Sicre, and Hervé Jégou. 2015. Particular object retrieval with integral max-pooling of CNN activations. CoRR abs/1511.05879 (2015).

[33]

Alexander Toshev and Christian Szegedy. 2014. Deeppose: Human pose estimation via deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1653--1660.

Digital Library

[34]

Danai Triantafyllidou, Paraskevi Nousi, and Anastasios Tefas. 2017. Lightweight two-stream convolutional face detection. In Signal Processing Conference (EU-SIPCO), 2017 25th European. IEEE, 1190--1194.

[35]

Maria Tzelepi and Anastasios Tefas. 2016. Exploiting supervised learning for finetuning deep CNNs in Content Based Image Retrieval. In 23nd International Conference on Pattern Recognition (ICPR). IEEE.

[36]

Maria Tzelepi and Anastasios Tefas. 2016. Relevance Feedback in Deep Convolutional Neural Networks for Content Based Image Retrieval. In Proceedings of the 9th Hellenic Conference on Artificial Intelligence (SETN '16). ACM, Article 27, 7 pages.

Digital Library

[37]

Maria Tzelepi and Anastasios Tefas. 2018. Deep convolutional image retrieval: A general framework. Signal Processing: Image Communication 63 (2018), 30--43.

[38]

Ellen M Voorhees. 1985. The cluster hypothesis revisited. In Proceedings of the 8th annual international ACM SIGIR conference on Research and development in information retrieval. ACM, 188--196.

Digital Library

[39]

Ji Wan, Dayong Wang, Steven Chu Hong Hoi, Pengcheng Wu, Jianke Zhu, Yong-dong Zhang, and Jintao Li. 2014. Deep learning for content-based image retrieval: A comprehensive study. In Proceedings of the ACM International Conference on Multimedia. ACM, 157--166.

Digital Library

[40]

Wei Yu, Kuiyuan Yang, Hongxun Yao, Xiaoshuai Sun, and Pengfei Xu. 2017. Exploiting the complementary strengths of multi-layer CNN features for image retrieval. Neurocomputing 237 (2017), 235--241.

Digital Library

[41]

Wan-Lei Zhao, Hervé Jégou, and Guillaume Gravier. 2013. Oriented pooling for dense and non-dense rotation-invariant features. In BMVC-24th British Machine Vision Conference.

Cited By

Hire DPatil ACharles P(2023)Efficient rotated and scaled digital image retrieval model using deep learning-based hybrid features extractionMultimedia Tools and Applications10.1007/s11042-023-17016-y83:12(34733-34758)Online publication date: 27-Sep-2023
https://doi.org/10.1007/s11042-023-17016-y

Index Terms

Fully Unsupervised Convolutional Learning for Fast Image Retrieval
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Neural networks
2. Information systems
  1. Information retrieval
    1. Specialized information retrieval
      1. Multimedia and multimodal retrieval
        Image search

Recommendations

Deep convolutional learning for Content Based Image Retrieval

In this paper we propose a model retraining method for learning more efficient convolutional representations for Content Based Image Retrieval. We employ a deep CNN model to obtain the feature representations from the activations of the convolutional ...
Relevance Feedback in Deep Convolutional Neural Networks for Content Based Image Retrieval
SETN '16: Proceedings of the 9th Hellenic Conference on Artificial Intelligence

In this paper a novel Relevance Feedback approach that uses deep Convolutional Neural Networks (CNNs) for image retrieval is proposed. We utilize a deep CNN model to refine the feature representations of the deeper layer used for the retrieval, based on ...
Content-based image retrieval with compact deep convolutional features

Convolutional neural networks (CNNs) with deep learning have recently achieved a remarkable success with a superior performance in computer vision applications. Most of CNN-based methods extract image features at the last layer using a single CNN ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

SETN '18: Proceedings of the 10th Hellenic Conference on Artificial Intelligence

July 2018

339 pages

ISBN:9781450364331

DOI:10.1145/3200947

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

In-Cooperation

EETN: Hellenic Artificial Intelligence Society
UOP: University of Patras
University of Thessaly: University of Thessaly, Volos, Greece

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 July 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

SETN '18

SETN '18: 10th Hellenic Conference on Artificial Intelligence

July 9 - 12, 2018

Patras, Greece

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
144
Total Downloads

Downloads (Last 12 months)4
Downloads (Last 6 weeks)0

Reflects downloads up to 07 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Hire DPatil ACharles P(2023)Efficient rotated and scaled digital image retrieval model using deep learning-based hybrid features extractionMultimedia Tools and Applications10.1007/s11042-023-17016-y83:12(34733-34758)Online publication date: 27-Sep-2023
https://doi.org/10.1007/s11042-023-17016-y

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents