ABSTRACT
Results returned by commercial image search engines should include relevant and diversified depictions of queries in order to ensure good coverage of users' information needs. While relevance has drastically improved in recent years, diversity is still an open problem. In this paper we propose a reranking method that could be implemented on top of such engines in order to provide a better balance between relevance and diversity. Our method formulates the reranking problem as an optimization of a utility function that jointly considers relevance and diversity. Our main contribution is the replacement of the unsupervised definition of relevance that is commonly used in this formulation with a supervised classification model that strives to capture a query and application-specific notion of relevance. This model provides more accurate relevance scores that lead to significantly improved diversification performance. Furthermore, we propose a stacking-type ensemble learning approach that allows combining multiple features in a principled way when computing the relevance of an image. An empirical evaluation carried out on the datasets of the MediaEval 2013 and 2014 "Retrieving Diverse Social Images" (RDSI) benchmarks confirms the superior performance of the proposed method compared to other participating systems as well as a state-of-the-art, unsupervised reranking method.
- T. Arni, P. Clough, M. Sanderson, and M. Grubinger. Overview of the imageclefphoto 2008 photographic retrieval task. In Evaluating Systems for Multilingual and Multimodal Information Access, pages 500--511. 2009. Google ScholarDigital Library
- A. Babenko, A. Slesarev, A. Chigorin, and V. Lempitsky. Neural codes for image retrieval. In ECCV, 2014.Google ScholarCross Ref
- J. Carbonell and J. Goldstein. The use of mmr, diversity-based reranking for reordering documents and producing summaries. In SIGIR, pages 335--336, 1998. Google ScholarDigital Library
- H. Chen and D. R. Karger. Less is more: probabilistic models for retrieving fewer relevant documents. In SIGIR, pages 429--436, 2006. Google ScholarDigital Library
- D. Corney, C. Martin, A. Göker, E. Spyromitros-Xioufis, S. Papadopoulos, Y. Kompatsiaris, L. Aiello, and B. Thomee. Socialsensor: Finding diverse images at mediaeval 2013. In MediaEval, 2013.Google Scholar
- D.-T. Dang-Nguyen, L. Piras, G. Giacinto, G. Boato, and F. De Natale. Retrieval of diverse images by pre-filtering and hierarchical clustering. In MediaEval, 2014.Google Scholar
- T. Deselaers, T. Gass, P. Dreuw, and H. Ney. Jointly optimising relevance and diversity in image retrieval. In ACM CIVR '09, New York, USA, 2009. Google ScholarDigital Library
- R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research, 9:1871--1874, 2008. Google ScholarDigital Library
- B. Ionescu, M. Menéndez, H. Müller, and A. Popescu. Retrieving diverse social images at MediaEval 2013: Objectives, dataset and evaluation. In MediaEval, 2013.Google Scholar
- B. Ionescu, A. Popescu, M. Lupu, A. Gînsca, and H. Müller. Retrieving diverse social images at MediaEval 2014: Challenge, dataset and evaluation. In MediaEval, 2014.Google Scholar
- N. Jain, J. Hare, S. Samangooei, J. Preston, J. Davies, D. Dupplaw, and P. H. Lewis. Experiments in diversifying flickr result sets. In MediaEval, 2013.Google Scholar
- Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093, 2014.Google Scholar
- E. Spyromitros-Xioufis, S. Papadopoulos, I. Kompatsiaris, G. Tsoumakas, and I. Vlahavas. A comprehensive study over vlad and product quantization in large-scale image retrieval. IEEE Transactions on Multimedia, 2014.Google ScholarCross Ref
- E. Spyromitros-Xioufis, S. Papadopoulos, Y. Kompatsiaris, and I. Vlahavas. Socialsensor: Finding diverse images at mediaeval 2014. In MediaEval, 2014.Google Scholar
- R. H. van Leuken, L. Garcia, X. Olivares, and R. van Zwol. Visual diversification of image search results. In WWW, pages 341--350, 2009. Google ScholarDigital Library
- D. H. Wolpert. Stacked generalization. Neural networks, 5(2):241--259, 1992. Google ScholarDigital Library
- C. X. Zhai, W. W. Cohen, and J. Lafferty. Beyond independent relevance: methods and evaluation metrics for subtopic retrieval. In SIGIR, pages 10--17, 2003. Google ScholarDigital Library
Index Terms
- Improving Diversity in Image Search via Supervised Relevance Scoring
Recommendations
Jointly optimising relevance and diversity in image retrieval
CIVR '09: Proceedings of the ACM International Conference on Image and Video RetrievalIn this paper we present a method to jointly optimise the relevance and the diversity of the results in image retrieval. Without considering diversity, image retrieval systems often mainly find a set of very similar results, so called near duplicates, ...
Image Search Reranking with Relevance, Diversity and Topic Coverage
ICIMCS'16: Proceedings of the International Conference on Internet Multimedia Computing and ServiceImage search reranking has recently been proposed to improve image search results. Most of the conventional reranking methods cannot leverage both relevance and diversity of the search results simultaneously. In addition, they usually ignore the latent ...
Relevance Feedback and Learning in Content-Based Image Search
A major bottleneck in content-based image retrieval (CBIR) systems or search engines is the large gap between low-level image features used to index images and high-level semantic contents of images. One solution to this bottleneck is to apply relevance ...
Comments