Boundary-Aware Hashing for Hamming Space Retrieval

Hamming space retrieval is a hot area of research in deep hashing because it is effective for large-scale image retrieval. Existing hashing algorithms have not fully used the absolute boundary to discriminate the data inside and outside the Hamming ball, and the performance is not satisfying. In this paper, a boundary-aware contrastive loss is designed. It involves an exponential function with absolute boundary (i.e., Hamming radius) information for dissimilar pairs and a logarithmic function to encourage small distance for similar pairs. It achieves a push that is bigger than the pull inside the Hamming ball, and the pull is bigger than the push outside the ball. Furthermore, a novel Boundary-Aware Hashing (BAH) architecture is proposed. It discriminatively penalizes the dissimilar data inside and outside the Hamming ball. BAH enables the influence of extremely imbalanced data to be reduced without up-weight to similar pairs or other optimization strategies because its exponential function rapidly converges outside the absolute boundary, making a huge contrast difference between the gradients of the logarithmic and exponential functions. Extensive experiments conducted on four benchmark datasets show that the proposed BAH obtains higher performance for different code lengths, and it has the advantage of handling extremely imbalanced data.

Download Full-text

A Combination of Spatial Pyramid and Inverted Index for Large-Scale Image Retrieval

Computer Vision ◽

10.4018/978-1-5225-5204-8.ch054 ◽

2018 ◽

pp. 1307-1321

Author(s):

Vinh-Tiep Nguyen ◽

Thanh Duc Ngo ◽

Minh-Triet Tran ◽

Duy-Dinh Le ◽

Duc Anh Duong

Keyword(s):

Image Retrieval ◽

Large Scale ◽

Spatial Information ◽

Real Life ◽

Inverted Index ◽

Bag Of Words ◽

Visual Words ◽

Benchmark Datasets ◽

Large Scale Image Retrieval ◽

Inverted Indexing

Large-scale image retrieval has been shown remarkable potential in real-life applications. The standard approach is based on Inverted Indexing, given images are represented using Bag-of-Words model. However, one major limitation of both Inverted Index and Bag-of-Words presentation is that they ignore spatial information of visual words in image presentation and comparison. As a result, retrieval accuracy is decreased. In this paper, the authors investigate an approach to integrate spatial information into Inverted Index to improve accuracy while maintaining short retrieval time. Experiments conducted on several benchmark datasets (Oxford Building 5K, Oxford Building 5K+100K and Paris 6K) demonstrate the effectiveness of our proposed approach.

Download Full-text

A Combination of Spatial Pyramid and Inverted Index for Large-Scale Image Retrieval

International Journal of Multimedia Data Engineering and Management ◽

10.4018/ijmdem.2015040103 ◽

2015 ◽

Vol 6 (2) ◽

pp. 37-51 ◽

Cited By ~ 2

Author(s):

Vinh-Tiep Nguyen ◽

Thanh Duc Ngo ◽

Minh-Triet Tran ◽

Duy-Dinh Le ◽

Duc Anh Duong

Keyword(s):

Image Retrieval ◽

Large Scale ◽

Spatial Information ◽

Real Life ◽

Inverted Index ◽

Bag Of Words ◽

Visual Words ◽

Benchmark Datasets ◽

Large Scale Image Retrieval ◽

Inverted Indexing

Download Full-text

Deep Joint Semantic-Embedding Hashing

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/332 ◽

2018 ◽

Cited By ~ 11

Author(s):

Ning Li ◽

Chao Li ◽

Cheng Deng ◽

Xianglong Liu ◽

Xinbo Gao

Keyword(s):

Large Scale ◽

Semantic Level ◽

Semantic Correlation ◽

Semantic Embedding ◽

Proposed Model ◽

Label Information ◽

Benchmark Datasets ◽

Large Scale Image Retrieval ◽

Almost All ◽

Hash Codes

Hashing has been widely deployed to large-scale image retrieval due to its low storage cost and fast query speed. Almost all deep hashing methods do not sufficiently discover semantic correlation from label information, which results in the learned hash codes less discriminative. In this paper, we propose a novel Deep Joint Semantic-Embedding Hashing (DSEH) approach that contains LabNet and ImgNet. Specifically, LabNet is explored to capture abundant semantic correlation between sample pairs and supervise ImgNet from semantic level and hash codes level, which is conductive to the generated hash codes being more discriminative and similarity-preserving. Extensive experiments on three benchmark datasets show that the proposed model outperforms the state-of-the-art methods.

Download Full-text

PRELIMINARY ESTIMATION OF POSTSEISMIC DEFORMATION PARAMETERS FROM CONTINUOUS GPS DATA IN KOREA PENINSULA AND IEODO AFTER THE 2011 TOHOKU-OKI MW9.0 EARTHQUAKE

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-w1-55-2016 ◽

2016 ◽

Vol XLII-4/W1 ◽

pp. 55-59

Author(s):

W. A. W. Aris ◽

T. A. Musa ◽

H. Lee ◽

Y. Choi ◽

H. Yoon

Keyword(s):

Exponential Function ◽

Deformation Characteristic ◽

Postseismic Deformation ◽

Tectonic Deformation ◽

Gps Data ◽

Research Station ◽

Logarithmic Function ◽

Exponential Functions ◽

Deformation Parameters ◽

Continuous Gps

This paper describes utilization of GPS data in Korea Peninsula and IEODO ocean research station for investigation of postseismic deformation characteristic after the 2011 Tohoku-oki Mw9.0 Earthquake. Analytical logarithmic and exponential functions were used to evaluate the postseismic deformation parameters. The results found that the data in Korea Peninsula and IEODO during periods of mid-2011 – mid-2014 are fit better using logarithmic function with deformation decay at 134.5 ±0.1 days than using the exponential function. The result also clearly indicates that further investigation into postseismic deformation over longer data span should be taken into account to explain tectonic deformation over the region.

Download Full-text

Generalized Probability Functions

Advances in Mathematical Physics ◽

10.1155/2009/206176 ◽

2009 ◽

Vol 2009 ◽

pp. 1-13 ◽

Cited By ~ 5

Author(s):

Alexandre Souto Martinez ◽

Rodrigo Silva González ◽

César Augusto Sangaletti Terçariol

Keyword(s):

Exponential Function ◽

Error Function ◽

Generalized Functions ◽

Probability Density Functions ◽

Density Functions ◽

Logarithmic Function ◽

Rank Distribution ◽

Exponential Functions ◽

Generalized Exponential Function ◽

Generalized Probability

From the integration of nonsymmetrical hyperboles, a one-parameter generalization of the logarithmic function is obtained. Inverting this function, one obtains the generalized exponential function. Motivated by the mathematical curiosity, we show that these generalized functions are suitable to generalize some probability density functions (pdfs). A very reliable rank distribution can be conveniently described by the generalized exponential function. Finally, we turn the attention to the generalization of one- and two-tail stretched exponential functions. We obtain, as particular cases, the generalized error function, the Zipf-Mandelbrot pdf, the generalized Gaussian and Laplace pdf. Their cumulative functions and moments were also obtained analytically.

Download Full-text

Binary Coding based Label Distribution Learning

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/386 ◽

2018 ◽

Author(s):

Ke Wang ◽

Xin Geng

Keyword(s):

Large Scale ◽

State Of The Art ◽

Binary Codes ◽

Binary Coding ◽

Benchmark Datasets ◽

Hamming Space ◽

The Mean ◽

Label Distribution Learning ◽

Distribution Generation ◽

Label Distribution

Label Distribution Learning (LDL) is a novel learning paradigm in machine learning, which assumes that an instance is labeled by a distribution over all labels, rather than labeled by a logic label or some logic labels. Thus, LDL can model the description degree of all possible labels to an instance. Although many LDL methods have been put forward to deal with different application tasks, most existing methods suffer from the scalability issue. In this paper, a scalable LDL framework named Binary Coding based Label Distribution Learning (BC-LDL) is proposed for large-scale LDL. The proposed framework includes two parts, i.e., binary coding and label distribution generation. In the binary coding part, the learning objective is to generate the optimal binary codes for the instances. We integrate the label distribution information of the instances into a binary coding procedure, leading to high-quality binary codes. In the label distribution generation part, given an instance, the k nearest training instances in the Hamming space are searched and the mean of the label distributions of all the neighboring instances is calculated as the predicted label distribution. Experiments on five benchmark datasets validate the superiority of BC-LDL over several state-of-the-art LDL methods.

Download Full-text

Large-scale Semantic Parsing without Question-Answer Pairs

Transactions of the Association for Computational Linguistics ◽

10.1162/tacl_a_00190 ◽

2014 ◽

Vol 2 ◽

pp. 377-392 ◽

Cited By ~ 40

Author(s):

Siva Reddy ◽

Mirella Lapata ◽

Mark Steedman

Keyword(s):

Natural Language ◽

Large Scale ◽

Graph Matching ◽

State Of The Art ◽

The State ◽

Semantic Parsing ◽

Matching Problem ◽

Weak Supervision ◽

Benchmark Datasets

In this paper we introduce a novel semantic parsing approach to query Freebase in natural language without requiring manual annotations or question-answer pairs. Our key insight is to represent natural language via semantic graphs whose topology shares many commonalities with Freebase. Given this representation, we conceptualize semantic parsing as a graph matching problem. Our model converts sentences to semantic graphs using CCG and subsequently grounds them to Freebase guided by denotations as a form of weak supervision. Evaluation experiments on a subset of the Free917 and WebQuestions benchmark datasets show our semantic parser improves over the state of the art.

Download Full-text

Incremental Community Detection on Large Complex Attributed Network

ACM Transactions on Knowledge Discovery from Data ◽

10.1145/3451216 ◽

2021 ◽

Vol 15 (6) ◽

pp. 1-20

Author(s):

Zhe Chen ◽

Aixin Sun ◽

Xiaokui Xiao

Keyword(s):

Community Detection ◽

Large Scale ◽

Network Data ◽

Topological Information ◽

Community Membership ◽

Attributed Network ◽

Benchmark Datasets ◽

Modularity Maximization ◽

Large Scale Networks

Community detection on network data is a fundamental task, and has many applications in industry. Network data in industry can be very large, with incomplete and complex attributes, and more importantly, growing. This calls for a community detection technique that is able to handle both attribute and topological information on large scale networks, and also is incremental. In this article, we propose inc-AGGMMR, an incremental community detection framework that is able to effectively address the challenges that come from scalability, mixed attributes, incomplete values, and evolving of the network. Through construction of augmented graph, we map attributes into the network by introducing attribute centers and belongingness edges. The communities are then detected by modularity maximization. During this process, we adjust the weights of belongingness edges to balance the contribution between attribute and topological information to the detection of communities. The weight adjustment mechanism enables incremental updates of community membership of all vertices. We evaluate inc-AGGMMR on five benchmark datasets against eight strong baselines. We also provide a case study to incrementally detect communities on a PayPal payment network which contains users with transactions. The results demonstrate inc-AGGMMR’s effectiveness and practicability.

Download Full-text