Abstract
Unsupervised hashing has attracted much attention for binary representation learning due to the requirement of economical storage and efficiency of binary codes. It aims to encode high-dimensional features in the Hamming space with similarity preservation between instances. However, most existing methods learn hash functions in manifold-based approaches. Those methods capture the local geometric structures (i.e., pairwise relationships) of data, and lack satisfactory performance in dealing with real-world scenarios that produce similar features (e.g., color and shape) with different semantic information. To address this challenge, in this work, we propose an effective unsupervised method, namely, Jointly Personalized Sparse Hashing (JPSH), for binary representation learning. To be specific, first, we propose a novel personalized hashing module, i.e., Personalized Sparse Hashing (PSH). Different personalized subspaces are constructed to reflect category-specific attributes for different clusters, adaptively mapping instances within the same cluster to the same Hamming space. In addition, we deploy sparse constraints for different personalized subspaces to select important features. We also collect the strengths of the other clusters to build the PSH module with avoiding over-fitting. Then, to simultaneously preserve semantic and pairwise similarities in our proposed JPSH, we incorporate the proposed PSH and manifold-based hash learning into the seamless formulation. As such, JPSH not only distinguishes the instances from different clusters but also preserves local neighborhood structures within the cluster. Finally, an alternating optimization algorithm is adopted to iteratively capture analytical solutions of the JPSH model. We apply the proposed representation learning algorithm JPSH to the similarity search task. Extensive experiments on four benchmark datasets verify that the proposed JPSH outperforms several state-of-the-art unsupervised hashing algorithms.
- [1] . 2015. Learning deep features for image emotion classification. In Proceedings of the IEEE International Conference on Image Processing. IEEE, 4491–4495.Google Scholar
Digital Library
- [2] . 2009. NUS-WIDE: A real-world web image database from National University of Singapore. In Proceedings of the ACM International Conference on Image and Video Retrieval. 1–9.Google Scholar
Digital Library
- [3] . 2004. Locality-sensitive hashing scheme based on p-stable distributions. In Proceedings of the Annual Symposium on Computational Geometry. 253–262.Google Scholar
Digital Library
- [4] . 2021. Unsupervised deep K-means hashing for efficient image retrieval and clustering. IEEE Trans. Circ. Syst. Video Technol. 31, 8 (2021), 3266–3277.Google Scholar
Cross Ref
- [5] . 2020. Unsupervised remote sensing image retrieval using probabilistic latent semantic hashing. IEEE Geosci. Remote Sens. Lett. 18, 2 (2020), 256–260.Google Scholar
Cross Ref
- [6] . 2012. Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 35, 12 (2012), 2916–2929.Google Scholar
Digital Library
- [7] . 2015. Network lasso: Clustering and optimization in large graphs. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 387–396.Google Scholar
Digital Library
- [8] . 2017. Unsupervised t-distributed video hashing and its deep hashing extension. IEEE Trans. Image Process. 26, 11 (2017), 5531–5544.Google Scholar
Digital Library
- [9] . 2018. Discrete spectral hashing for efficient similarity retrieval. IEEE Trans. Image Process. 28, 3 (2018), 1080–1091.Google Scholar
Cross Ref
- [10] . 2020. Creating something from nothing: Unsupervised knowledge distillation for cross-modal hashing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3123–3132.Google Scholar
Cross Ref
- [11] . 2008. The MIR flickr retrieval evaluation. In Proceedings of the ACM International Conference on Multimedia Information Retrieval. 39–43.Google Scholar
Digital Library
- [12] . 2001. A small approximately min-wise independent family of hash functions. J. Algor. 38, 1 (2001), 84–90.Google Scholar
Digital Library
- [13] . 2014. Locally linear hashing for extracting non-linear manifolds. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2115–2122.Google Scholar
Digital Library
- [14] . 2017. Toward optimal manifold hashing via discrete locally linear embedding. IEEE Trans. Image Process. 26, 11 (2017), 5411–5420.Google Scholar
Digital Library
- [15] . 2015. Scalable graph hashing with feature transformation. In Proceedings of the International Joint Conference on Artificial Intelligence, Vol. 15. 2248–2254.Google Scholar
- [16] . 2018. Deep semantic-preserving ordinal hashing for cross-modal similarity search. IEEE Trans. Neural Netw. Learn. Syst. 30, 5 (2018), 1429–1440.Google Scholar
Cross Ref
- [17] . 2021. Unsupervised discrete hashing with affinity similarity. IEEE Trans. Image Process. 30 (2021), 6130–6141.Google Scholar
Cross Ref
- [18] . 2014. Exclusive feature learning on arbitrary structures via l1,2-norm. Adv. Neural Info. Process. Syst. 27 (2014), 1655–1663.Google Scholar
- [19] . 2016. Uncorrelated group lasso. In Proceedings of the AAAI Conference on Artificial Intelligence. 1765–1771.Google Scholar
Cross Ref
- [20] . 2009. Learning multiple layers of features from tiny images. Citeseer.Google Scholar
- [21] . 2017. Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 6 (2017), 84–90.Google Scholar
Digital Library
- [22] . 2018. Jointly sparse hashing for image retrieval. IEEE Trans. Image Process. 27, 12 (2018), 6147–6158.Google Scholar
Cross Ref
- [23] . 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278–2324.Google Scholar
Cross Ref
- [24] . 2018. Unsupervised personalized feature selection. In Proceedings of the AAAI Conference on Artificial Intelligence. 3514–3521.Google Scholar
Cross Ref
- [25] . 2017. Toward personalized relational learning. In Proceedings of the SIAM International Conference on Data Mining. SIAM, 444–452.Google Scholar
Cross Ref
- [26] . 2022. Structure-adaptive neighborhood preserving hashing for scalable video search. IEEE Trans. Circ. Syst. Video Technol. 32, 4 (2022), 2441–2454.Google Scholar
Cross Ref
- [27] . 2017. Large graph hashing with spectral rotation. In Proceedings of the AAAI Conference on Artificial Intelligence. 2203–2209.Google Scholar
Cross Ref
- [28] . 2020. Weakly supervised semantic guided hashing for social image retrieval. Int. J. Comput. Vision 128, 8 (2020), 2265–2278.Google Scholar
Digital Library
- [29] . 2018. Supervised online hashing via hadamard codebook learning. In Proceedings of the ACM International Conference on Multimedia. 1635–1643.Google Scholar
Digital Library
- [30] . 2015. Semantics-preserving hashing for cross-view retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3864–3872.Google Scholar
Cross Ref
- [31] . 2018. Ordinal constraint binary coding for approximate nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 41, 4 (2018), 941–955.Google Scholar
Digital Library
- [32] . 2016. Towards optimal binary code learning via ordinal embedding. In Proceedings of the AAAI Conference on Artificial Intelligence. 1258–1265.Google Scholar
Cross Ref
- [33] . 2010. Large graph construction for scalable semi-supervised learning. In Proceedings of the International Conference on International Conference on Machine Learning. 679–686.Google Scholar
Digital Library
- [34] . 2014. Discrete graph hashing. Advances in Neural Information Processing Systems 27 (2014), 3419–3427.Google Scholar
- [35] . 2011. Hashing with graphs. In Proceedings of the International Conference on Machine Learning. 1–8.Google Scholar
Digital Library
- [36] . 2001. Modeling the shape of the scene: A holistic representation of the spatial envelope. Int. J. Comput. Vision 42, 3 (2001), 145–175.Google Scholar
Digital Library
- [37] . 2020. Learning multi-level deep representations for image emotion classification. Neural Process. Lett. 51, 3 (2020), 2043–2061.Google Scholar
Digital Library
- [38] . 2019. Multi-level region-based convolutional neural network for image emotion classification. Neurocomputing 333 (2019), 429–439.Google Scholar
Digital Library
- [39] . 2013. Inductive hashing on manifolds. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1562–1569.Google Scholar
Digital Library
- [40] . 2020. Towards universal representation learning for deep face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6817–6826.Google Scholar
Cross Ref
- [41] . 2018. Discriminative deep quantization hashing for face image retrieval. IEEE Trans. Neural Netw. Learn. Syst. 29, 12 (2018), 6154–6162.Google Scholar
Cross Ref
- [42] . 2020. Unsupervised hashing based on the recovery of subspace structures. Pattern Recogn. 103 (2020), 107261.Google Scholar
Cross Ref
- [43] . 2008. Visualizing data using t-SNE.J. Mach. Learn. Res. 9, 11 (2008).Google Scholar
- [44] . 2009. Feature hashing for large scale multitask learning. In Proceedings of the Annual International Conference on Machine Learning. 1113–1120.Google Scholar
Digital Library
- [45] . 2008. Spectral hashing. Adv. Neural Info. Process. Syst. 21 (2008), 1753–1760.Google Scholar
- [46] . 2020. Concatenation hashing: A relative position preserving method for learning binary codes. Pattern Recogn. 100 (2020), 107151.Google Scholar
Digital Library
- [47] . 2015. Sparse projections for high-dimensional binary codes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3332–3339.Google Scholar
- [48] . 2021. Sub-Region localized hashing for fine-grained image retrieval. IEEE Trans. Image Process. 31 (2021), 314–326.Google Scholar
Cross Ref
- [49] . 2018. Semantic structure-based unsupervised deep hashing. In Proceedings of the International Joint Conference on Artificial Intelligence. 1064–1070.Google Scholar
Cross Ref
- [50] . 2020. Adaptive deep metric learning for affective image retrieval and classification. IEEE Trans. Multimedia 23 (2020), 1640–1653.Google Scholar
Digital Library
- [51] . 2019. Attention-aware polarity sensitive embedding for affective image retrieval. In Proceedings of the IEEE International Conference on Computer Vision. 1140–1150.Google Scholar
Cross Ref
- [52] . 2020. Deep unsupervised hybrid-similarity hadamard hashing. In Proceedings of the ACM International Conference on Multimedia. 3274–3282.Google Scholar
Digital Library
- [53] . 2019. SADIH: Semantic-aware discrete hashing. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 5853–5860.Google Scholar
Digital Library
- [54] . 2014. Affective image retrieval via multi-graph learning. In Proceedings of the ACM International Conference on Multimedia. 1025–1028.Google Scholar
Digital Library
- [55] . 2018. Exploring auxiliary context: Discrete semantic transfer hashing for scalable image retrieval. IEEE Trans. Neural Netw. Learn. Syst. 29, 11 (2018), 5264–5276.Google Scholar
Cross Ref
- [56] . 2017. Graph PCA hashing for similarity search. IEEE Trans. Multimedia 19, 9 (2017), 2033–2044.Google Scholar
Digital Library
- [57] . 2014. A sparse embedding and least variance encoding approach to hashing. IEEE Trans. Image Process. 23, 9 (2014), 3737–3750.Google Scholar
Cross Ref
- [58] . 2006. Sparse principal component analysis. J. Comput. Graph. Stat. 15, 2 (2006), 265–286.Google Scholar
Cross Ref
Index Terms
Binary Representation via Jointly Personalized Sparse Hashing
Recommendations
Weighted hashing for fast large scale similarity search
CIKM '13: Proceedings of the 22nd ACM international conference on Information & Knowledge ManagementSimilarity search, or finding approximate nearest neighbors, is an important technique for many applications. Many recent research demonstrate that hashing methods can achieve promising results for large scale similarity search due to its computational ...
A posteriori multi-probe locality sensitive hashing
MM '08: Proceedings of the 16th ACM international conference on MultimediaEfficient high-dimensional similarity search structures are essential for building scalable content-based search systems on feature-rich multimedia data. In the last decade, Locality Sensitive Hashing (LSH) has been proposed as indexing technique for ...
Topology preserving hashing for similarity search
MM '13: Proceedings of the 21st ACM international conference on MultimediaBinary hashing has been widely used for efficient similarity search. Learning efficient codes has become a research focus and it is still a challenge. In many cases, the real-world data often lies on a low-dimensional manifold, which should be taken ...






Comments