Semi-supervised hashing for scalable image retrieval

By Jun Wang, Ondrej Kumar, Shih-Fu Chang. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

656 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bb963c63ee55eab58371bc4ba0690f3eb0f498a8

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

A Modulation Module for Multi-task Learning with Applications in Image Retrieval (2018, background): “We do not study the efficiency problem in image retrieval as in many prior works [23,26,24,25].”
Scalable Nearest Neighbor Algorithms for High Dimensional Data (2014, methodology): “computed using various learning techniques: parameter sensitive hashing [5], spectral hashing [32], randomized LSH hashing from learned metrics [33], kernelized LSH [34], learnt binary embeddings [35], shift-invariant kernel hashing [36], semi-supervised hashing [37], optimized kernel hashing [38] a”
Collective Matrix Factorization Hashing for Multimodal Data (2014, methodology): “As extensions of standard LSH, some machine learning methods are employed to design effective compact hashing, such as Manifold Learning, Supervised Learning, Kernel Learning, Deep Learning, Quantization Learning, Linear Discriminant Analysis (LDA), K-means and PCA, which respectively generate Spect”
Linear cross-modal hashing for efficient multimedia search (2013, methodology): “Following the literature [18, 30], we prune original NUS-WIDE to form a new dataset NUS-WIDE consisting of 195, 969 image-tag pairs by keeping the pairs that belong to one of the 21 most frequent tags, such as “animal”, “buildings”, “person”, etc.”
Fast Neighborhood Graph Search Using Cartesian Concatenation (2013, methodology): “LSH [32], and shift kernel hashing [33], semi-supervised hashing [34], (multidimensional) spectral hashing [35, 36], iterative quantization [37], complementary hashing [38] and order preserving hashing [39].”
Learning Compact Binary Face Descriptor for Face Recognition (2015, methodology): “While most previous binary codes learning methods were developed for visual search [14], [15], [17], [55], [60], [62], they are also applicable to face recognition even if there is no such study before.”
Optimized Product Quantization (2014, methodology): “Binary embedding is a popular way of encoding vectors [9], [15], [16], [17], [18], [19], [27].”
Deep Cross-Modal Hashing (2016, background): “…fast retrieval speed, hashing has recently attracted much attention from the ANN research community (Weiss et al., 2008; Raginsky & Lazebnik, 2009; Wang et al., 2010; Liu et al., 2011; Norouzi & Fleet, 2011; Norouzi et al., 2012; Rastegari et al., 2013; Yu et al., 2014; Liu et al., 2014;…”
SCH-GAN: Semi-Supervised Cross-Modal Hashing by Generative Adversarial Network (2018, methodology): “an be efﬁciently implemented. (2) Binary codes take much less storage compared with original high dimensional feature. A large amount of hashing methods are designed for single modality retrieval [1]–[8], that is to say, data can only be retrieved by an query of the same modality, such as image retr”
Hashing for Similarity Search: A Survey (2014, methodology): “spectral hashing [135] E LE HD CC + BB + BU kernelized spectral hashing [37] S, E KE HD CC + BB + BU Hypergraph spectral hashing [153], [89] S CL HD CC + BB + BU Topology preserving hashing [145] E LI HD CC + CCD + BB + BU hashing with graphs [83] S KE HD CC + BB ICA Hashing [35] E LI, KE HD CC + BB”
K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes (2013, methodology): “We follow the search strategy of Hamming ranking commonly adopted in many hashing methods [1, 31, 29, 19, 5, 6].”
Semi-Supervised Hashing for Large-Scale Search (2012, methodology): “Following the criterion used in [37][13], a returned point is considered a good neighbor if it lies in the top 2 percentile points closest to a query.”
A Survey on Learning to Hash (2016, background): “Semi-supervised hashing [141], [142], [143] is the representative algorithm in this group.”
Feature Learning Based Deep Supervised Hashing with Pairwise Labels (2015, methodology): “Representative pairwise label based methods include sequential projection learning for hashing (SPLH) [Wang et al., 2010], minimal loss hashing (MLH) [Norouzi and Fleet, 2011], supervised hashing with kernels (KSH) [Liu et al., 2012], two-step hashing (TSH) [Lin et al., 2013], fast supervised hashin”
Deep learning of binary hash codes for fast image retrieval (2015, background): “Several hashing algorithms [6, 29, 18, 20, 28, 10] have been proposed to approximately identify data relevant to the query.”
Online sketching hashing (2015, methodology): “In many existing hashing works, the data is first normalized to have zero mean before training [33, 9], or assumed to be inherently zero-centered, then bk = 0 for any hash function hk(x).”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “In this case, a plethora of methods have been proposed (Kulis and Darrell 2009; Wang et al. 2010; Strecha et al. 2012; Liu et al. 2012a; Norouzi and Blei 2011; Gong et al. 2013; Shakhnarovich 2005), among which image matching is considered an important experimental validation task.”