Deep Hashing with Hash Center Update for Efficient Image Retrieval

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 maximized. The first loss, maximizes the correlation between the hash centers and learned hash codes. The second loss maximizes the correlation between the class labels and classification scores. A novel weighted mean and thresholding based hash center update scheme is proposed for adapting the hash centers in each epoch. 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 an efficient feature space for image retrieval. The measured mean average precision shows that the proposed approach outperforms other state-of-theart approaches in both single-labeled and multi-labeled image datasets.

[1]  N. L. Johnson,et al.  Multivariate Analysis , 1958, Nature.

[2]  Robert H. Riffenburgh,et al.  Linear Discriminant Analysis , 1960 .

[3]  Jens-Rainer Ohm,et al.  Optimized Feature Space Learning for Generating Efficient Binary Codes for Image Retrieval , 2020, Signal Process. Image Commun..

[4]  M. Bartlett.  Further aspects of the theory of multiple regression , 1938, Mathematical Proceedings of the Cambridge Philosophical Society.

[5]  Antonio Torralba,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition , 2022 .

[6]  Svetlana Lazebnik,et al.  Iterative quantization: A procrustean approach to learning binary codes , 2011, CVPR 2011.

[7]  Tat-Seng Chua,et al.  NUS-WIDE: a real-world web image database from National University of Singapore , 2009, CIVR '09.

[8]  Tieniu Tan,et al.  Deep Supervised Discrete Hashing , 2017, NIPS.

[9]  Jianmin Wang,et al.  Deep Hashing Network for Efficient Similarity Retrieval , 2016, AAAI.

[10]  Jiashi Feng,et al.  Central Similarity Quantization for Efficient Image and Video Retrieval , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Yi Shi,et al.  Deep Supervised Hashing with Triplet Labels , 2016, ACCV.

[12]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[13]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[14]  Hanjiang Lai,et al.  Simultaneous feature learning and hash coding with deep neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Philip S. Yu,et al.  HashNet: Deep Learning to Hash by Continuation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[16]  Wu-Jun Li,et al.  Deep Discrete Supervised Hashing , 2017, IEEE Transactions on Image Processing.

[17]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[18]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[19]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Hanjiang Lai,et al.  Supervised Hashing for Image Retrieval via Image Representation Learning , 2014, AAAI.

[21]  Wu-Jun Li,et al.  Feature Learning Based Deep Supervised Hashing with Pairwise Labels , 2015, IJCAI.

[22]  Weixiang Hong,et al.  Image Hashing via Linear Discriminant Learning , 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).