Deep Hashing with Hash Center Update for Efficient Image Retreival

Abin Jose, Daniel Filbert, Christian Rohlfing, Jens Rainer Ohm

Submitted to IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP 2022),
Conference homepage


In this paper, we propose an approach for learning binary hash codes for image retrieval. Canonical Correlation Analysis (CCA) is used to design two loss functions for training a neural network such that the correlation between the two views to CCA is maximum. The first loss maximizes the correlation between the hash centers and the learned hash codes. The second loss maximizes the correlation between the class labels and the classification scores. In this paper, a novel weighted mean and thresholding-based hash center update scheme for adapting the hash centers is proposed. The training loss reaches the theoretical lower bound of the proposed loss functions, showing that the correlation coefficients are maximized during training and substantiating the formation of efficient feature space for retrieval. The measured mean average precision shows that the proposed approach outperforms other state-of-the-art methods.

Supplementary Material

Ablation study, T-SNE plots, and retrieval results

NOTICE FOR IEEE PUBLICATIONS: © IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE. Contact: Manager, Copyrights and Permissions / IEEE Service Center / 445 Hoes Lane / P.O. Box 1331 / Piscataway, NJ 08855-1331, USA. Telephone: + Intl. 908-562-3966.