Deep Supervised Hashing for Fast Image Retrieval

By Haomiao Liu, Ruiping Wang, Shiguang Shan, Xilin Chen. International Journal of Computer Vision, 2016

960 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f4cf5b16f0d0360b7d9b1eafd02eed7d9858c8df

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. Tao A. Xiang
3. Jiashi Feng
4. Luc Van Gool
5. Shiv Ram Dubey
6. Yi Yang
7. Xiaogang Wang
8. Qi Tian

Citations in the corpus

• A Survey on Learning to Hash (2016, background): “H Drop ICA hashing [39] (2011) BB + BMIM Linear Drop Kernelized spectral hashing [40] (2010) BB + BU Kernel Drop Hashing with graphs [86] (2011) BB + BU Eigenfunction Drop Discrete graph hashing [84] (2014) BB + BU Kernel Discretize Kernelized Discrete graph hashing [128] (2016) BB + BU Kernel Discr”
• Deep Cauchy Hashing for Hamming Space Retrieval (2018, background): “Recently, deep learning to hash methods [33, 17, 28, 8, 36, 1, 21, 4] yield breakthrough results on image retrieval datasets by blending the power of deep learning [15, 13].”
• Learning Deep Representations with Probabilistic Knowledge Transfer (2018, methodology): “osed method was evaluated using the CIFAR10 dataset [25], that contains 60,000 32 32 color images that belongs to 10 different categories and it is frequently used for evaluating retrieval techniques [28, 19]. The knowledge was transfered from the penultimate layer of a deep neural network, the ResN”
• A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, methodology): “image retrieval [86], [89], [93], [135], semi-supervised image retrieval [115], cross-modal retrieval [143], [144], sketch based image retrieval [145], [146], object retrieval [147], [148], etc.”
• Complementary Incremental Hashing With Query-Adaptive Re-Ranking for Image Retrieval (2020, background): “Deep supervised hashing [30] learns hash codes based on the similarity information of image pairs.”
• Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search (2020, background): “Similarly, deep supervised hashing (DSH) [59] also adopts a pairwise loss function; moreover, the regularization is imposed to decrease the quantization error between real-valued outputs and binary codes.”
• 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.”
• SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval (2018, methodology): “In the initial attempt, feature representation and hashing codes were learned in separate stages [28], where subsequent work [14, 35, 15] suggested superior practice through joint end-to-end training.”
• Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (2018, methodology): “The deep learning based supervised hashing methods which simultaneously learn image representations and coding functions [18], [26], [27], [59], have recently shown great performance improvement compared to previous handcrafted feature based shallow models.”
• Deep Cross-Modal Hashing (2016, methodology): “There also exist some methods which adopt deep learning for uni-modal hashing [37, 23, 20, 40, 24].”