Feature Learning Based Deep Supervised Hashing with Pairwise Labels

By Wu-Jun Li, Sheng Wang, Wang-Cheng Kang. International Joint Conference on Artificial Intelligence, 2015

737 citations recorded by the source corpus.

Recent years have witnessed wide application of hashing for large-scale image retrieval. However, most existing hashing methods are based on handcrafted features which might not be optimally compatible with the hashing procedure. Recently, deep hashing methods have been proposed to perform simultaneous feature learning and hash-code learning with deep neural networks, which have shown better performance than traditional hashing methods with hand-crafted features. Most of these deep hashing methods are supervised whose supervised information is given with triplet labels. For another common application scenario with pairwise labels, there have not existed methods for simultaneous feature learning and hash-code learning. In this paper, we propose a novel deep hashing method, called deep pairwise-supervised hashing (DPSH), to perform simultaneous feature learning and hashcode learning for applications with pairwise labels. Experiments on real datasets show that our DPSH method can outperform other methods to achieve the state-of-the-art performance in image retrieval applications.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/707b5787330d5e66d97a3da27f586f58a68780e8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Hashing Network for Unsupervised Domain Adaptation (2017, methodology): “We used the DPSH algorithm [30] to train a deep network on the target data and used it to generate hash codes on a validation subset.”
Deep Cross-Modal Hashing (2016, methodology): “There also exist some methods which adopt deep learning for uni-modal hashing [37, 23, 20, 40, 24].”
Deep Supervised Discrete Hashing (2017, methodology): “Besides the triplet ranking based methods, some pairwise label based deep hashing methods are also exploited [9, 25].”
HashNet: Deep Learning to Hash by Continuation (2017, methodology): “h) the quantization error function by binarizing continuous codes g into binary codes h. Prior methods control the quantization error in two ways: (a) minL(g) + Q(g;h) through continuous optimization [44,22]; (b)minL(h)+Q(g;h)through discrete optimization on L(h) but continuous optimization on Q(g;h”
Deep Supervised Hashing for Fast Image Retrieval (2016, methodology): “Specifically, as a representative family of such methods, many hashing algorithms (Gionis et al. 1999; Gong and Lazebnik 2011; Jiang and Li 2017; Kang et al. 2016; Kulis and Darrell 2009; Lai et al. 2015; Li et al. 2016; Lin et al. 2015a; Liu et al. 2017, 2014, 2012; Norouzi and Fleet 2011; Rastegar”
Learning Discrete Representations via Information Maximizing Self-Augmented Training (2017, background): “Regarding hashing learning, a number of studies have used deep neural networks for supervised hash learning and achieved state-of-the-art results on image and text retrievals (Xia et al., 2014; Lai et al., 2015; Zhang et al., 2015; Xu et al., 2015; Li et al., 2015).”
Deep Cauchy Hashing for Hamming Space Retrieval (2018, background): “Recently, deep learning to hash methods [33, 17, 28, 8, 36, 19, 21, 4] have shown that deep neural networks can enable end-toend representation learning and hash coding with nonlinear hash functions.”
Binary Generative Adversarial Networks for Image Retrieval (2017, methodology): “Another issue is a non-smooth sign-activation function used to generate the binary codes, which, despite several ideas proposed to tackle it [2, 6, 26], still makes the standard back-propagation infeasible.”
Fine-Grained Image Analysis With Deep Learning: A Survey (2021, methodology): “Image hashing [201], [202] is a popular and effective technique for approximate nearest neighbor search, and has the potential to help with large-scale”
Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (2018, methodology): “To overcome this shortcoming, the recently proposed methods [18], [19], [59] perform simultaneous feature learning and hash code learning.”
Unsupervised Semantic-Preserving Adversarial Hashing for Image Search (2019, methodology): “Deep learning-based hashing methods [41], [42] have also been proposed for efficient ANN search, showing that deep networks can help in the more effective learning of hash codes.”
Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search (2020, methodology): “Note that DPSH and HashNet are both DH methods, which adopt the same deep architecture as TSDH, and also use a similar pairwise loss function; the key difference here is that the pairwise loss function for both DPSH and HashNet are used for the image modality only and, thus, cannot fully exploit the”
A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, methodology): “In 2016, pairwise labels are exploited to learn the CNN feature for image retrieval [97], [98].”
Central Similarity Quantization for Efficient Image and Video Retrieval (2019, methodology): “Recently, “deep learning to hash” methods [14, 32, 21, 18, 22, 44] have been successfully applied to large-scale image retrieval [44, 48] and video retrieval [8, 28, 21], which can naturally represent a nonlinear hash function for producing hash codes of input data.”
All the News That Fits in Bits: Learned Rotation-Aware Binary Projections for Efficient News Retrieval at NDTV (2026, unknown): “A parallel line learns binary codes throughsuperviseddeepnetworks,spanningpairwise[16],continuation-based[1],andvariationalorcontrastiveobjectives[2,11]([3,17] forsurveys).”