Fast Supervised Hashing with Decision Trees for High-Dimensional Data

Lin, Guosheng; Shen, Chunhua; Shi, Qinfeng; Hengel, Anton van den; Suter, David

doi:10.1109/cvpr.2014.253

Cited by 380 publications

(304 citation statements)

References 20 publications

Supporting

Mentioning

303

Contrasting

Order By: Relevance

“…The basic idea is to exploit deep learning methods to extract deep features automatically, meanwhile use the similarity in functional behaviors as the supervised information to guide the deep feature learning process. Besides, we use learning to hash [Kong and Li, 2012] to further transform the real-valued representations to binary hash codes in the purpose of improving the detection efficiency and saving storage space. Specifically, we formulate the clone detection problem as a supervised deep feature learning problem via pairwise labels where clone pairs are regarded as positive examples and non-clone pairs are negative pairs.…”

Section: Introductionmentioning

confidence: 99%

Supervised Deep Features for Software Functional Clone Detection by Exploiting Lexical and Syntactical Information in Source Code

Wei

2017

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

246

205

View full text Add to dashboard Cite

Software clone detection, aiming at identifying out code fragments with similar functionalities, has played an important role in software maintenance and evolution. Many clone detection approaches have been proposed. However, most of them represent source codes with hand-crafted features using lexical or syntactical information, or unsupervised deep features, which makes it difficult to detect the functional clone pairs, i.e., pieces of codes with similar functionality but differing in both syntactical and lexical level. In this paper, we address the software functional clone detection problem by learning supervised deep features. We formulate the clone detection as a supervised learning to hash problem and propose an end-to-end deep feature learning framework called CDLH for functional clone detection. Such framework learns hash codes by exploiting the lexical and syntactical information for fast computation of functional similarity between code fragments. Experiments on software clone detection benchmarks indicate that the CDLH approach is effective and outperforms the state-of-the-art approaches in software functional clone detection.

show abstract

Section: Introductionmentioning

confidence: 99%

Supervised Deep Features for Software Functional Clone Detection by Exploiting Lexical and Syntactical Information in Source Code

Wei

2017

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

246

205

View full text Add to dashboard Cite

show abstract

“…In [Lai et al, 2015], NINH is proposed to improve CNNH by fusing the hash learning into the deep structure. NINH learns hash codes by minimizing the triplet ranking loss based on the "network in network" network [Lin et al, 2013]. DSH [Liu et al, 2016] learns hash codes by preserving the similarity encoded in the input pairs of images (similar/dissimilar) based on a CNN architecture.…”

Section: Deep Hashing Methodsmentioning

confidence: 99%

“…DSH [Liu et al, 2016] learns hash codes based on a CNN architecture by preserving the similarity encoded in the input pairs of images (similar/dissimilar). NINH [Lai et al, 2015] learns hash codes by minimizing the triplet ranking loss based on the "network in network" network [Lin et al, 2013]. In [Dong et al, 2016], the low-rank hashing first pre-learns hash functions based on the CNN features and introduces the fine-tuning procedure based on the triplet ranking loss.…”

Section: Introductionmentioning

confidence: 99%

Discriminative Deep Hashing for Scalable Face Image Retrieval

Lin

Tang

2017

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

With the explosive growth of images containing faces, scalable face image retrieval has attracted increasing attention. Due to the amazing effectiveness, deep hashing has become a popular hashing method recently. In this work, we propose a new Discriminative Deep Hashing (DDH) network to learn discriminative and compact hash codes for large-scale face image retrieval. The proposed network incorporates the end-to-end learning, the divide-and-encode module and the desired discrete code learning into a unified framework. Specifically, a network with a stack of convolution-pooling layers is proposed to extract multi-scale and robust features by merging the outputs of the third max pooling layer and the fourth convolutional layer. To reduce the redundancy among hash codes and the network parameters simultaneously, a divide-andencode module to generate compact hash codes. Moreover, a loss function is introduced to minimize the prediction errors of the learned hash codes, which can lead to discriminative hash codes. Extensive experiments on two datasets demonstrate that the proposed method achieves superior performance compared with some state-of-the-art hashing methods.

show abstract

“…More specifically, unsupervised hashing does not utilize the label information of training examples [21][22][23][24]. On the contrary, supervised hashing methods try to incorporate semantic (label) information for hashing function learning [25][26][27][28][29][30]. Although hashing learning has been successfully applied in the natural image retrieval, few studies have been devoted to hashing learning-based RS image retrieval.…”

Section: Introductionmentioning

confidence: 99%

Multiple Feature Hashing Learning for Large-Scale Remote Sensing Image Retrieval

Tao

et al. 2017

IJGI

View full text Add to dashboard Cite

Driven by the urgent demand of remote sensing big data management and knowledge discovery, large-scale remote sensing image retrieval (LSRSIR) has attracted more and more attention. As is well known, hashing learning has played an important role in coping with big data mining problems. In the literature, several hashing learning methods have been proposed to address LSRSIR. Until now, existing LSRSIR methods take only one type of feature descriptor as the input of hashing learning methods and ignore the complementary effects of multiple features, which may represent remote sensing images from different aspects. Different from the existing LSRSIR methods, this paper proposes a flexible multiple-feature hashing learning framework for LSRSIR, which takes multiple complementary features as the input and learns the hybrid feature mapping function, which projects multiple features of the remote sensing image to the low-dimensional binary (i.e., compact) feature representation. Furthermore, the compact feature representations can be directly utilized in LSRSIR with the aid of the hamming distance metric. In order to show the superiority of the proposed multiple feature hashing learning method, we compare the proposed approach with the existing methods on two publicly available large-scale remote sensing image datasets. Extensive experiments demonstrate that the proposed approach can significantly outperform the state-of-the-art approaches.

show abstract

Fast Supervised Hashing with Decision Trees for High-Dimensional Data

Cited by 380 publications

References 20 publications

Supervised Deep Features for Software Functional Clone Detection by Exploiting Lexical and Syntactical Information in Source Code

Supervised Deep Features for Software Functional Clone Detection by Exploiting Lexical and Syntactical Information in Source Code

Discriminative Deep Hashing for Scalable Face Image Retrieval

Multiple Feature Hashing Learning for Large-Scale Remote Sensing Image Retrieval

Contact Info

Product

Resources

About