Journal Article10.1109/TPAMI.2017.2699960
A Survey on Learning to Hash
TL;DR: In this paper, a comprehensive survey of the learning to hash algorithms is presented, categorizing them according to the manners of preserving the similarities into: pairwise similarity preserving, multi-wise similarity preservation, implicit similarity preserving and quantization, and discuss their relations.
read more
Abstract: Nearest neighbor search is a problem of finding the data points from the database such that the distances from them to the query point are the smallest. Learning to hash is one of the major solutions to this problem and has been widely studied recently. In this paper, we present a comprehensive survey of the learning to hash algorithms, categorize them according to the manners of preserving the similarities into: pairwise similarity preserving, multiwise similarity preserving, implicit similarity preserving, as well as quantization, and discuss their relations. We separate quantization from pairwise similarity preserving as the objective function is very different though quantization, as we show, can be derived from preserving the pairwise similarities. In addition, we present the evaluation protocols, and the general performance analysis, and point out that the quantization algorithms perform superiorly in terms of search accuracy, search time cost, and space cost. Finally, we introduce a few emerging topics.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
An Embarrassingly Simple Approach to Discrete Supervised Hashing
Shuguang Zhao,Bingzhi Chen,Zheng Zhang,Guangming Lu +3 more
TL;DR: This paper proposes Discrete Auto-Encoder Hashing (DAEH), a novel framework that leverages semantic labels to refine latent feature embeddings and optimize hashing functions, outperforming state-of-the-art hashing baselines on Caltech-256, CIFAR-10, and MNIST datasets.
Neural Networks Behave As Hash Encoders: an Empirical Study
Fengxiang He,Shiye Lei,Jianmin Ji,Dacheng Tao +3 more
TL;DR: This study reveals that well-trained neural networks exhibit hash encoder behavior, partitioning input space into linear regions with unique activation patterns, enabling deterministic and categorical encoding properties without extra effort.
Discriminative Visual Similarity Search with Semantically Cycle-consistent Hashing Networks
TL;DR: This paper proposes a novel deep tripartite semantically interactive hashing framework, dubbed Semantically Cycle-consistent Hashing Networks (SCHN), for discriminative hash code learning, and establishes the cyclic principle of deep semantic-preserving hashing by adaptive semantic parsing across different spaces in a single-modal visual similarity search.
Multi-label Image Deep Hashing with Hybrid Loss of Global Center and Local Alignment
Ye Liu,Yan Pan,Jian Yin +2 more
TL;DR: Multi-label image deep hashing with hybrid loss of global center and local alignment improves image retrieval performance by combining global and local constraints.
Discrete Listwise Content-Aware Recommendation
Fangyuan Luo,Jun Wu,Tao Wang +2 more
TL;DR: In this article , a ranking-based CAR hashing method based on Factorization Machine (FM), called Discrete Listwise FM (DLFM), is proposed for fast and accurate recommendation.
References
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- 20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
- 01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
53.5K
Glove: Global Vectors for Word Representation
Jeffrey Pennington,Richard Socher,Christopher D. Manning +2 more
- 01 Oct 2014
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Related Papers (5)
Fumin Shen,Chunhua Shen,Wei Liu,Heng Tao Shen +3 more
- 07 Jun 2015
Wei Liu,Jun Wang,Rongrong Ji,Yu-Gang Jiang,Shih-Fu Chang +4 more
- 16 Jun 2012