Supervised learning through neuronal response modulation

Neural networks that are trained to perform specific tasks must be developed through a supervised learning procedure. This normally takes the form of direct supervision of synaptic plasticity. We explore the idea that supervision takes place instead through the modulation of neuronal excitability. Such supervision can be done using conventional synaptic feedback pathways rather than requiring the hypothetical actions of unknown modulatory agents. During task learning, supervised response modulation guides Hebbian synaptic plasticity indirectly by establishing appropriate patterns of correlated network activity. This results in robust learning of function approximation tasks evenwhenmultiple output units representing different functions share large amounts of common input. Reward-based supervision is also studied, and a number of potential advantages of neuronal response modulation are identified.     

Supervised deep hashing for image content security

Multimedia Tools and Applications - Due to the fast growth of image data on the web, it is necessary to ensure the content security of uploaded images. One of the fundamental problems behind this...     

基于离散哈希的聚类

传统的聚类方法是在数据空间进行,且聚类数据的维度较高.为了解决这两个问题,提出了一种新的二进制图像聚类方法——基于离散哈希的聚类(CDH).该框架通过L21范数实现自适应的特征选择,从而降低数据的维度;同时通过哈希方法将数据映射到二进制的汉明空间,随后,在汉明空间中对稀疏的二进制矩阵进行低秩矩阵分解,完成图像的快速聚类...     

Efficient model similarity estimation with robust hashing

Software and Systems Modeling - As model-driven engineering (MDE) is increasingly adopted in complex industrial scenarios, modeling artefacts become a key and strategic asset for companies. As...     

深度非对称离散跨模态哈希方法

大多数深度监督跨模态哈希方法采用对称的方式学习哈希码,导致其不能有效利用大规模数据集中的监督信息;并且对于哈希码的离散约束问题,常采用的基于松弛的策略会产生较大的量化误差,导致哈希码次优。针对以上问题,提出深度非对称离散跨模态哈希（DADCH）方法。首先构造了深度神经网络和字典学习相结合的非对称学习框架,以学习查询实例和数据库实例的哈希码,从而更有效地挖掘数据的监督信息,减少模型的训练时间;然后采用离散优化算法逐列优化哈希码矩阵,降低哈希码二值化的量化误差;同时为充分挖掘数据的语义信息,在神经网络中添加了标签层进行标签预测,并利用语义信息嵌入将不同类别的判别信息通过线性映射嵌入到哈希码中,增强哈希码的判别性。实验结果表明,在IAPR-TC12、MIRFLICKR-25K和NUS-WIDE数据集上,哈希码长度为64 bit时,所提方法在图像检索文本时的平均精度均值（mAP）较近年来提出的先进的深度跨模态检索方法——自监督对抗哈希（SSAH）分别高出约11.6、5.2、14.7个百分点。     

Robust hashing for multi-view data: Jointly learning low-rank kernelized similarity consensus and hash functions

Learning hash functions/codes for similarity search over multi-view data is attracting increasing attention, where similar hash codes are assigned to the data objects characterizing consistently neighborhood relationship across views. Traditional methods in this category inherently suffer three limitations: 1) they commonly adopt a two-stage scheme where similarity matrix is first constructed, followed by a subsequent hash function learning; 2) these methods are commonly developed on the assumption that data samples with multiple representations are noise-free,which is not practical in real-life applications; and 3) they often incur cumbersome training model caused by the neighborhood graph construction using all N points in the database (O(N)). In this paper, we motivate the problem of jointly and efficiently training the robust hash functions over data objects with multi-feature representations which may be noise corrupted. To achieve both the robustness and training efficiency, we propose an approach to effectively and efficiently learning low-rank kernelized¹ hash functions shared across views. Specifically, we utilize landmark graphs to construct tractable similarity matrices in multi-views to automatically discover neighborhood structure in the data. To learn robust hash functions, a latent low-rank kernel function is used to construct hash functions in order to accommodate linearly inseparable data. In particular, a latent kernelized similarity matrix is recovered by rank minimization on multiple kernel-based similarity matrices. Extensive experiments on real-world multi-view datasets validate the efficacy of our method in the presence of error corruptions.We use kernelized similarity rather than kernel, as it is not a squared symmetric matrix for data-landmark affinity matrix.     

语义相似性保持的判别式跨模态哈希

针对跨模态哈希检索方法中存在标签语义利用不充分,从而导致哈希码判别能力弱、检索精度低的问题,提出了一种语义相似性保持的判别式跨模态哈希方法.该方法将异构模态的特征数据投影到一个公共子空间,并结合多标签核判别分析方法将标签语义中的判别信息和潜在关联嵌入到公共子空间中;通过最小化公共子空间与哈希码之间的量化误差提高哈希码的判别能力;此外,利用标签构建语义相似性矩阵,并将语义相似性保留到所学的哈希码中,进一步提升哈希码的检索精度.在LabelMe、MIRFlickr-25k、NUS-WIDE三个基准数据集上进行了大量实验,其结果验证了该方法的有效性.     

Supervised tensor learning

Tensor representation is helpful to reduce the small sample size problem in discriminative subspace selection. As pointed by this paper, this is mainly because the structure information of objects in computer vision research is a reasonable constraint to reduce the number of unknown parameters used to represent a learning model. Therefore, we apply this information to the vector-based learning and generalize the vector-based learning to the tensor-based learning as the supervised tensor learning (STL) framework, which accepts tensors as input. To obtain the solution of STL, the alternating projection optimization procedure is developed. The STL framework is a combination of the convex optimization and the operations in multilinear algebra. The tensor representation helps reduce the overfitting problem in vector-based learning. Based on STL and its alternating projection optimization procedure, we generalize support vector machines, minimax probability machine, Fisher discriminant analysis, and distance metric learning, to support tensor machines, tensor minimax probability machine, tensor Fisher discriminant analysis, and the multiple distance metrics learning, respectively. We also study the iterative procedure for feature extraction within STL. To examine the effectiveness of STL, we implement the tensor minimax probability machine for image classification. By comparing with minimax probability machine, the tensor version reduces the overfitting problem. We focus on the convex optimization-based binary classification learning algorithms in this paper. This is because the solution to a convex optimization-based learning algorithm is unique. Dacheng Tao received the B.Eng. degree from the University of Science and Technology of China (USTC), the MPhil degree from the Chinese University of Hong Kong (CUHK) and the PhD from the University of London (Birkbeck). He will join the Department of Computing in the Hong Kong Polytechnic University as an assistant professor. His research interests include biometric research, discriminant analysis, support vector machine, convex optimization for machine learning, multilinear algebra, multimedia information retrieval, data mining, and video surveillance. He published extensively at TPAMI, TKDE, TIP, TMM, TCSVT, CVPR, ICDM, ICASSP, ICIP, ICME, ACM Multimedia, ACM KDD, etc. He gained several Meritorious Awards from the Int’l Interdisciplinary Contest in Modeling, which is the highest level mathematical modeling contest in the world, organized by COMAP. He is a guest editor for special issues of the Int’l Journal of Image and Graphics (World Scientific) and the Neurocomputing (Elsevier). Xuelong Li works at the University of London. He has published in journals (IEEE T-PAMI, T-CSVT, T-IP, T-KDE, TMM, etc.) and conferences (IEEE CVPR, ICASSP, ICDM, etc.). He is an Associate Editor of IEEE T-SMC, Part C, Neurocomputing, IJIG (World Scientific), and Pattern Recognition (Elsevier). He is also an Editor Board Member of IJITDM (World Scientific) and ELCVIA (CVC Press). He is a Guest Editor for special issues of IJCM (Taylor and Francis), IJIG (World Scientific), and Neurocomputing (Elsevier). He co-chaired the 5th Annual UK Workshop on Computational Intelligence and the 6th the IEEE Int’l Conf. on Machine Learning and Cybernetics. He was also a publicity chair of the 7th IEEE Int’l Conf. on Data Mining and the 4th Int’l Conf. on Image and Graphics. He has been on the program committees of more than 50 conferences and workshops. Xindong Wu is a Professor and the Chair of the Department of Computer Science at the University of Vermont. He holds a Ph.D. in Artificial Intelligence from the University of Edinburgh, Britain. His research interests include data mining, knowledge-based systems, and Web information exploration. He has published extensively in these areas in various journals and conferences, including IEEE TKDE, TPAMI, ACM TOIS, IJCAI, AAAI, ICML, KDD, ICDM, and WWW, as well as 12 books and conference proceedings. Dr. Wu is the Editor-in-Chief of the IEEE Transactions on Knowledge and Data Engineering (by the IEEE Computer Society), the Founder and current Steering Committee Chair of the IEEE International Conference on Data Mining (ICDM), an Honorary Editor-in-Chief of Knowledge and Information Systems (by Springer), and a Series Editor of the Springer Book Series on Advanced Information and Knowledge Processing (AIKP). He is the 2004 ACM SIGKDD Service Award winner. Weiming Hu received the Ph.D. degree from the Department of Computer Science and Engineering, Zhejiang University. From April 1998 to March 2000, he was a Postdoctoral Research Fellow with the Institute of Computer Science and Technology, Founder Research and Design Center, Peking University. Since April 1998, he has been with the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences. Now he is a Professor and a Ph.D. Student Supervisor in the laboratory. His research interests are in visual surveillance, neural networks, filtering of Internet objectionable information, retrieval of multimedia, and understanding of Internet behaviors. He has published more than 80 papers on national and international journals, and international conferences. Stephen J. Maybank received a BA in Mathematics from King’s college, Cambridge in 1976 and a PhD in Computer Science from Birkbeck College, University of London in 1988. He was a research scientist at GEC from 1980 to 1995, first at MCCS, Frimley and then, from 1989, at the GEC Marconi Hirst Research Centre in London. In 1995 he became a lecturer in the Department of Computer Science at the University of Reading and in 2004 he became a professor in the School of Computer Science and Information Systems at Birkbeck College, University of London. His research interests include camera calibration, visual surveillance, tracking, filtering, applications of projective geometry to computer vision and applications of probability, statistics and information theory to computer vision. He is the author of more than 90 scientific publications and one book. He is a Fellow of the Institute of Mathematics and its Applications, a Fellow of the Royal Statistical Society and a Senior Member of the IEEE. For further information see http://www.dcs.bbk.ac.uk/~sjmaybank.     

自监督深度离散哈希图像检索

目的 基于深度学习的图像哈希检索是图像检索领域的热点研究问题。现有的深度哈希方法忽略了深度图像特征在深度哈希函数训练中的指导作用,并且由于采用松弛优化,不能有效处理二进制量化误差较大导致的生成次优哈希码的问题。对此,提出一种自监督的深度离散哈希方法（self-supervised deep discrete hashing,SSDDH）。方法 利用卷积神经网络提取的深度特征矩阵和图像标签矩阵,计算得到二进制哈希码并作为自监督信息指导深度哈希函数的训练。构造成对损失函数,同时保持连续哈希码之间相似性以及连续哈希码与二进制哈希码之间的相似性,并利用离散优化算法求解得到哈希码,有效降低二进制量化误差。结果 将本文方法在3个公共数据集上进行测试,并与其他哈希算法进行实验对比。在CIFAR-10、NUS-WIDE（web image dataset from National University of Singapore）和Flickr数据集上,本文方法的检索精度均为最高,本文方法的准确率比次优算法DPSH（deep pairwise-supervised hashing）分别高3%、3%和1%。结论 本文提出的基于自监督的深度离散哈希的图像检索方法能有效利用深度特征信息和图像标签信息,并指导深度哈希函数的训练,且能有效减少二进制量化误差。实验结果表明,SSDDH在平均准确率上优于其他同类算法,可以有效完成图像检索任务。     

重构约束的离散矩阵因式分解跨模态哈希

针对目前跨模态哈希方法中存在的哈希码鲁棒性不足、量化误差较大的问题,提出一种重构约束的离散矩阵因式分解哈希算法.通过矩阵因式分解直接学习多模态数据的离散深层潜在语义,避免松弛-量化产生的大量误差;将学习的深层语义重构回原始数据,降低数据中冗余信息的影响,加强哈希码的鲁棒性与可区分性.该算法在Wiki、NUS-WIDE和...     

Online unsupervised cross-view discrete hashing for large-scale retrieval

Applied Intelligence - Cross-view hashing has shown great potential for large-scale retrieval due to its superiority in terms of computation and storage. In real-world applications, data emerges in...     

Deep hashing with top similarity preserving for image retrieval

Multimedia Tools and Applications - Hashing has drawn more and more attention in image retrieval due to its high search speed and low storage cost. Traditional hashing methods project the...     

基于知识蒸馏的深度无监督离散跨模态哈希

跨模态哈希因其低存储花费和高检索效率得到了广泛的关注.现有的大部分跨模态哈希方法需要额外的手工标签来提供实例间的关联信息,然而,预训练好的深度无监督跨模态哈希方法学习到的深度特征同样能提供相似信息;且哈希码学习过程中放松了离散约束,造成较大的量化损失.针对以上两个问题,提出基于知识蒸馏的深度无监督离散跨模态哈希(DUD...     

基于感知哈希和切块的视频相似度检测方法

长期以来视频侵权问题层出不穷,而检测视频相似度是视频侵权的重要手段.针对现有视频相似度检测方法中存在的多特征关系难以关联、时间复杂度高等问题,提出一种基于感知哈希和切块的快速对比方法.首先,利用视频的关键图像帧生成数字指纹集;然后,基于切块的方法构建相应的倒排索引,提高数字指纹间的对比速度;最后,根据得到的数字指纹间的...     

Robust image hashing using non-uniform sampling in discrete Fourier domain

This paper proposes a robust image hashing method in discrete Fourier domain that can be applied in such fields as image authentication and retrieval. In the pre-processing stage, image resizing and total variation based filtering are first used to regularize the input image. Then the secondary image is obtained by the rotation projection, and the robust frequency feature is extracted from the secondary image after discrete Fourier transform. More sampling points are chosen from the low- and middle-frequency component to represent the salient content of the image effectively, which is achieved by the non-uniform sampling. Finally, the intermediate sampling feature vectors are scrambled and quantized to produce the resulting binary hash securely. The security of the method depends entirely on the secret key. Experiments are conducted to show that the present method has satisfactory robustness against perceptual content-preserving manipulations and has also very low probability for collision of the hashes of distinct images.     

Fast graph similarity search via hashing and its application on image retrieval

Similarity search in graph databases has been widely investigated. It is worthwhile to develop a fast algorithm to support similarity search in large-scale graph databases. In this paper, we investigate a k-NN (k-Nearest Neighbor) similarity search problem by locality sensitive hashing (LSH). We propose an innovative fast graph search algorithm named LSH-GSS, which first transforms complex graphs into vectorial representations based on prototypes in the database and later accelerates a query in Euclidean space by employing LSH. Because images can be represented as attributed graphs, we propose an approach to transform attributed graphs into n-dimensional vectors and apply LSH-GSS to execute further image retrieval. Experiments on three real graph datasets and two image datasets show that our methods are highly accurate and efficient.     

Supervised rank aggregation based on query similarity for document retrieval

This paper is concerned with supervised rank aggregation, which aims to improve the ranking performance by combining the outputs from multiple rankers. However, there are two main shortcomings in previous rank aggregation approaches. First, the learned weights for base rankers do not distinguish the differences among queries. This is suboptimal since queries vary significantly in terms of ranking. Besides, most current aggregation functions do not directly optimize the evaluation measures in ranking. In this paper, the differences among queries are taken into consideration, and a supervised rank aggregation function is proposed. This aggregation function is directly optimizing the evaluation measure NDCG, referred to as RankAgg.NDCG, We prove that RankAgg.NDCG can achieve better NDCG performance than the linear combination of the base rankers. Experimental results performed on benchmark datasets show our approach outperforms a number of baseline approaches.     

Supervised machine learning using encrypted training data

International Journal of Information Security - Preservation of privacy in data mining and machine learning has emerged as an absolute prerequisite in many practical scenarios, especially when the...     

Supervised fuzzy reinforcement learning for robot navigation

This paper addresses a new method for combination of supervised learning and reinforcement learning (RL). Applying supervised learning in robot navigation encounters serious challenges such as inconsistent and noisy data, difficulty for gathering training data, and high error in training data. RL capabilities such as training only by one evaluation scalar signal, and high degree of exploration have encouraged researchers to use RL in robot navigation problem. However, RL algorithms are time consuming as well as suffer from high failure rate in the training phase. Here, we propose Supervised Fuzzy Sarsa Learning (SFSL) as a novel idea for utilizing advantages of both supervised and reinforcement learning algorithms. A zero order Takagi–Sugeno fuzzy controller with some candidate actions for each rule is considered as the main module of robot's controller. The aim of training is to find the best action for each fuzzy rule. In the first step, a human supervisor drives an E-puck robot within the environment and the training data are gathered. In the second step as a hard tuning, the training data are used for initializing the value (worth) of each candidate action in the fuzzy rules. Afterwards, the fuzzy Sarsa learning module, as a critic-only based fuzzy reinforcement learner, fine tunes the parameters of conclusion parts of the fuzzy controller online. The proposed algorithm is used for driving E-puck robot in the environment with obstacles. The experiment results show that the proposed approach decreases the learning time and the number of failures; also it improves the quality of the robot's motion in the testing environments.     

Distance learning for similarity estimation

In this paper, we present a general guideline to find a better distance measure for similarity estimation based on statistical analysis of distribution models and distance functions. A new set of distance measures are derived from the harmonic distance, the geometric distance, and their generalized variants according to the Maximum Likelihood theory. These measures can provide a more accurate feature model than the classical Euclidean and Manhattan distances. We also find that the feature elements are often from heterogeneous sources that may have different influence on similarity estimation. Therefore, the assumption of single isotropic distribution model is often inappropriate. To alleviate this problem, we use a boosted distance measure framework that finds multiple distance measures which fit the distribution of selected feature elements best for accurate similarity estimation. The new distance measures for similarity estimation are tested on two applications: stereo matching and motion tracking in video sequences. The performance of boosted distance measure is further evaluated on several benchmark data sets from the UCI repository and two image retrieval applications. In all the experiments, robust results are obtained based on the proposed methods.