Incorporation of Semantic Segmentation Information in Deep Hashing Techniques for Image Retrieval


Extracting discriminative image features for similarity search in nowadays large-scale databases becomes an imperative issue of paramount importance. To address the so called task of Approximate Nearest Neighbor (ANN) search in large visual dataset, deep hashing methods (i.e. approaches that make use of the recent deep learning paradigm in computer vision) have recently been introduced. In this paper, a novel approach to deep hashing is proposed, which incorporates local-level information, in the form of image semantic segmentation masks, during the hash code learning step. The proposed framework makes use of pixel-level classification labels, i.e. following a point-wise supervised learning methodology. Experimental evaluation in the significantly challenging domain of on-line terrorist propaganda video analysis, i.e. a highly diverse and heterogeneous application case, demonstrates the efficiency of the proposed approach.

  • K. Gkountakos, T. Semertzidis, G. T. Papadopoulos, P. Daras, "Incorporation of Semantic Segmentation Information in Deep Hashing Techniques for Image Retrieval", IEEE International Conference on Engineering, Technology and Innovation (23rd ICE/ITMC), Madeira Island, Portugal, 27-29 June, 2017.

  • Full document available here.
    Contact Information

    Dr. Petros Daras, Principal Researcher Grade Α
    1st km Thermi – Panorama, 57001, Thessaloniki, Greece
    P.O.Box: 60361
    Tel.: +30 2310 464160 (ext. 156)
    Fax: +30 2310 464164