Spherical hashing

By Jae-Pil Heo, Youngwoon Lee, Junfeng He, Shih-Fu Chang, Sung-eui Yoon. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

466 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/19d45865a92d5c1ecaf5c7e3a47573c6acb8c3d8

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

1. Dacheng Tao
2. Luc Van Gool
3. Chunhua Shen
4. Yi Yang
5. Xiaogang Wang
6. Ling Shao
7. Jingdong Wang
8. Ming-Hsuan Yang

Citations in the corpus

• 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].”
• Multiscale Quantization for Fast Similarity Search (2017, background): “Binary embedding based approaches [36, 24, 18, 13, 17, 25] focus on learning short binary codes, and can be searched efficiently in Hamming space.”
• Learning Compact Binary Face Descriptor for Face Recognition (2015, background): “In this section, we applied four widely used binary codes learning methods including PCA-iterative quantization (PCA-ITQ) [15], angular quantization-based binary coding (AQBC) [14], spectral hashing (SH) [62], and Spherical hashing (SPH) [17] to learn face feature representation.”
• DeepHash: Getting Regularization, Depth and Fine-Tuning Right (2015, background): “There is plenty of work on binary codes for descriptors like SIFT or GIST [9, 15, 16, 17, 10, 12, 18, 11, 19, 20, 21].”
• Deep Cross-Modal Hashing (2016, background): “Due to its low storage cost and fast retrieval speed, hashing has recently attracted much attention from the ANN research community [17, 34, 9, 15, 26, 10, 29, 21, 28, 4].”
• Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search (2020, methodology): “Various unsupervised hashing methods have been proposed in recent years [38]–[41], [45], [46].”
• Inter-media hashing for large-scale retrieval from heterogeneous data sources (2013, background): “Besides, various distance measures in the binarycode space, such as spherical hamming distance [14] and Manhattan distance [19] are considered to learn hash functions.”
• Large-Scale Supervised Multimodal Hashing with Semantic Correlation Maximization (2014, background): “…and Indyk 2008; Kulis and Darrell 2009; Lin, Ross, and Yagnik 2010; Wang, Kumar, and Chang 2010; Norouzi and Fleet 2011; Kong, Li, and Guo 2012; Heo et al. 2012; Liu et al. 2012a; Kong and Li 2012b; Norouzi, Fleet, and Salakhutdinov 2012; Strecha et al. 2012; Ge et al. 2013; Neyshabur et al.…”
• Fast Supervised Hashing with Decision Trees for High-Dimensional Data (2014, methodology): “We compare to some popular unsupervised hashing methods: LSH [7], ITQ [8], Anchor Graph Hashing (AGH) [17], Spherical Hashing (SPHER) [10], MDSH [26].”
• Online sketching hashing (2015, methodology): “Representative works include Iterative Quantization (ITQ) [9], Isotropic Hashing (IsoH) [17], Spherical Hashing (SpH) [12] and so on [25, 19, 24].”
• Hashing with binary autoencoders (2015, methodology): “…algorithms: thresholded PCA (tPCA), Iterative Quantization (ITQ) (Gong et al., 2013), Spectral Hashing (SH) (Weiss et al., 2009), Kernelized Locality-Sensitive Hashing (KLSH) (Kulis and Grauman, 2012), AnchorGraph Hashing (AGH) (Liu et al., 2011), and Spherical Hashing (SPH) (Heo et al., 2012).”
• Unsupervised Semantic-Preserving Adversarial Hashing for Image Search (2019, methodology): “• SpH [55] uses a hypersphere to formulate a spherical hash function, and also proposes an iterative optimization algorithm to learn the hash codes.”
• Learning to Hash for Indexing Big Data—A Survey (2015, methodology): “Representative unsupervised methods include spectral hashing [32], graph hashing [28], manifold hashing [60], iterative quantization hashing [61], kernalized locality sensitive hashing [21], [41], isotropic hashing [62], angular quantization hashing [63], and spherical hashing [64].”
• Deep hashing for compact binary codes learning (2015, methodology): “Table 4 shows the training and test time of different hashing methods on the CIFAR-10 dataset when 16-bit binary codes are used for evaluation , where the test time is computed for each query 0 200 400 600 800 1000 0 0.05 0.1 0.15 0.2 0.25 0.3 0.35 N Recall ITQ KMH Spherical SH PCAH DH (a) 16 bits 0”
• Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks (2016, methodology): “We compare DeepBit with several unsupervised hashing methods, including LSH [2], ITQ [14], PCAH [45], Semantic Hashing (SH) [34], Spectral hashing (SpeH) [46]), Spherical hashing (SphH) [17], KMH [16], and Deep Hashing (DH) [24] on the CIFAR-10 dataset.”
• Naive Bayes Super-Resolution Forest (2015, methodology): “The idea is to construct this fast search strategy based on Spherical Hashing [11] to get logarithmic-time access to the anchor points (and their corresponding linear mapping functions) obtained by K-SVD.”
• Inductive Hashing on Manifolds (2013, methodology): “We compare nine hashing algorithms including the proposed IMH-tSNE, IMH-LE and seven other unsupervised state-of-the-art methods: PCAH [31], SH [33], AGH [21] and STH [35], BRE [15], ITQ [9], Spherical Hashing (SpH) [11].”
• Hashing for Similarity Search: A Survey (2014, methodology): “The basic idea of spherical hashing [38] is to use a hypersphere to formulate a spherical hash function,”
• A Survey on Learning to Hash (2016, methodology): “Spherical hashing [41] uses a hypersphere to partition the space.”