A relevance feedback perspective to image search result diversification

An efficient information retrieval system should be able to provide search results which are in the same time relevant for the query but which cover different aspects, i.e., diverse, of it. In this paper we address the issue of image search result diversification. We propose a new hybrid approach that integrates both the automatization power of the machines and the intelligence of human observers via an optimized multi-class Support Vector Machine (SVM) classifier-based relevance feedback (RF). In contrast to existing RF techniques which focus almost exclusively on improving the relevance of the results, the novelty of our approach is in considering in priority the diversification. We designed several diversification strategies which operate on top of the SVM RF and exploit the classifiers' output confidence scores. Experimental validation conducted on a publicly available image retrieval diversification dataset show the benefits of this approach which outperforms other state-of-the-art methods.