Semi-Supervised Hashing for Large-Scale Search

By Jun Wang, Sanjiv Kumar, Shih-Fu Chang. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012

814 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/80953468bd75833b755e7e4c25abe009dfd84cf0

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

Hashing for Distributed Data (2015, methodology): “To perform fair evaluation, we adopt the Hamming ranking strategy which is commonly used in the literature (Wang et al., 2012; Liu et al., 2011).”
Pairwise Teacher-Student Network for Semi-Supervised Hashing (2019, background): “SPLH [27] adopts the bit-balanced constraint for regularization, but it does not consider the relationship be-tween samples.”
Simultaneous feature learning and hash coding with deep neural networks (2015, methodology): “The existing learning-based hashing methods can be categorized into un-supervised and supervised methods, based on whether supervised information (e.g., similarities or dissimilarities on data points) is involved.”
Learning in high-dimensional multimedia data: the state of the art (2015, methodology): “Latent Semantic Analysis (LSA) is a variant on the PCA idea presented in [11] and it has been employed on documents, images, videos and mu-sics [31].”
Isotropic Hashing (2012, background): “These two advantages make hashing become a promising choice for efficient ANN search in massive data sets [1, 5, 6, 9, 10, 14, 15, 17, 20, 21, 23, 26, 29, 30, 31, 32, 33, 34].”
Polysemous Codes (2016, methodology): “Many variants have been subsequently proposed, such as spectral hashing [52] or ITQ [21] – see also [43,55,50] for representative works.”
Large-Scale Supervised Multimodal Hashing with Semantic Correlation Maximization (2014, methodology): “From (6), we can ﬁnd that the goal of our method is to maximize the semantic correlation.”
Deep Metric Transfer for Label Propagation with Limited Annotated Data (2018, background): “zes a model on a smalled labeled dataset and bootstraps on the new data it predicts. This tends to fail when the labeled set is small. Our work is most closely related to label propagation approaches [6,37], and we propose metric transfer to signiﬁcantly improve the propagation performance. Few-shot”
Structure-Preserving Binary Representations for RGB-D Action Recognition (2016, methodology): “In our experiments, we compare the proposed method against seven general hashing algorithms including KSH [58], BRE [60], MLH [61], LSH [56], SpH [57], AGH [68], PCAH [69], BSSC [53] and RBM [70].”
Hashing for Similarity Search: A Survey (2014, background): “On the other hand, as an inspiration of LSH, the concept of “small code” or “compact code” has become the focus of many researchers from the CV community, and many learning-based hashing methods have come in to being [135][125][126][30][83][139][127][29][82][130][31].”
Deep Hashing Network for Efficient Similarity Retrieval (2016, methodology): “…using Hamming distance (Kulis and Darrell 2009; Gong and Lazebnik 2011; Norouzi and Blei 2011; Fleet, Punjani, and Norouzi 2012; Liu et al. 2012; Wang, Kumar, and Chang 2012; Liu et al. 2013; Gong et al. 2013; Yu et al. 2014; Xia et al. 2014; Zhang et al. 2014; Shen et al. 2015; Lai et al.…”
Deep Cauchy Hashing for Hamming Space Retrieval (2018, methodology): “Many learning to hash methods have been proposed to enable efficient ANN search by Hamming ranking of compact hash codes, including both supervised and unsupervised methods [16, 12, 26, 9, 22, 30, 25, 24, 35].”
Complementary Incremental Hashing With Query-Adaptive Re-Ranking for Image Retrieval (2020, background): “The Sequential Projection Learning Hashing [33] trains hash functions sequentially.”
Learning Visual Semantic Relationships for Efficient Visual Retrieval (2015, methodology): “Sowa et al. [16] proposed the semantic network for artificial intelligence and machine translation.”
Supervised hashing with kernels (2012, methodology): “For unsupervised hashing, principled linear projections like PCA Hashing (PCAH) [17] and its rotational variant [2] were suggested for better quantization rather than random projections.”
A Survey on Learning to Hash (2016, methodology): “Semi-supervised hashing [141], [142], [143] is the representative algorithm in this group.”
Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (2018, methodology): “, LSH [9], PCAH [47], ITQ [10], SH [49], AGH [31], DGH [29], SGH [14], LGHSR [20], and three deep unsupervised hashing methods, i.”
HashNet: Deep Learning to Hash by Continuation (2017, methodology): “Many learning to hash methods have been proposed to enable efficient ANN search of high-dimensional data by ranking the Hamming distance across compact binary hash codes [19, 12, 27, 9, 23, 34, 25, 11, 38, 39].”