Paper Group ANR 363
Linear-Complexity Exponentially-Consistent Tests for Universal Outlying Sequence Detection. Exact tensor completion with sum-of-squares. Guided Co-training for Large-Scale Multi-View Spectral Clustering. Deep Learning Interior Tomography for Region-of-Interest Reconstruction. Constraints, Lazy Constraints, or Propagators in ASP Solving: An Empirica …
Linear-Complexity Exponentially-Consistent Tests for Universal Outlying Sequence Detection
| Title | Linear-Complexity Exponentially-Consistent Tests for Universal Outlying Sequence Detection |
| Authors | Yuheng Bu, Shaofeng Zou, Venugopal V. Veeravalli |
| Abstract | The problem of universal outlying sequence detection is studied, where the goal is to detect outlying sequences among $M$ sequences of samples. A sequence is considered as outlying if the observations therein are generated by a distribution different from those generating the observations in the majority of the sequences. In the universal setting, we are interested in identifying all the outlying sequences without knowing the underlying generating distributions. In this paper, a class of tests based on distribution clustering is proposed. These tests are shown to be exponentially consistent with linear time complexity in $M$. Numerical results demonstrate that our clustering-based tests achieve similar performance to existing tests, while being considerably more computationally efficient. |
| Tasks | |
| Published | 2017-01-21 |
| URL | http://arxiv.org/abs/1701.06084v4 |
| http://arxiv.org/pdf/1701.06084v4.pdf | |
| PWC | https://paperswithcode.com/paper/linear-complexity-exponentially-consistent |
| Repo | |
| Framework | |
Exact tensor completion with sum-of-squares
| Title | Exact tensor completion with sum-of-squares |
| Authors | Aaron Potechin, David Steurer |
| Abstract | We obtain the first polynomial-time algorithm for exact tensor completion that improves over the bound implied by reduction to matrix completion. The algorithm recovers an unknown 3-tensor with $r$ incoherent, orthogonal components in $\mathbb R^n$ from $r\cdot \tilde O(n^{1.5})$ randomly observed entries of the tensor. This bound improves over the previous best one of $r\cdot \tilde O(n^{2})$ by reduction to exact matrix completion. Our bound also matches the best known results for the easier problem of approximate tensor completion (Barak & Moitra, 2015). Our algorithm and analysis extends seminal results for exact matrix completion (Candes & Recht, 2009) to the tensor setting via the sum-of-squares method. The main technical challenge is to show that a small number of randomly chosen monomials are enough to construct a degree-3 polynomial with precisely planted orthogonal global optima over the sphere and that this fact can be certified within the sum-of-squares proof system. |
| Tasks | Matrix Completion |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06237v3 |
| http://arxiv.org/pdf/1702.06237v3.pdf | |
| PWC | https://paperswithcode.com/paper/exact-tensor-completion-with-sum-of-squares |
| Repo | |
| Framework | |
Guided Co-training for Large-Scale Multi-View Spectral Clustering
| Title | Guided Co-training for Large-Scale Multi-View Spectral Clustering |
| Authors | Tyng-Luh Liu |
| Abstract | In many real-world applications, we have access to multiple views of the data, each of which characterizes the data from a distinct aspect. Several previous algorithms have demonstrated that one can achieve better clustering accuracy by integrating information from all views appropriately than using only an individual view. Owing to the effectiveness of spectral clustering, many multi-view clustering methods are based on it. Unfortunately, they have limited applicability to large-scale data due to the high computational complexity of spectral clustering. In this work, we propose a novel multi-view spectral clustering method for large-scale data. Our approach is structured under the guided co-training scheme to fuse distinct views, and uses the sampling technique to accelerate spectral clustering. More specifically, we first select $p$ ($\ll n$) landmark points and then approximate the eigen-decomposition accordingly. The augmented view, which is essential to guided co-training process, can then be quickly determined by our method. The proposed algorithm scales linearly with the number of given data. Extensive experiments have been performed and the results support the advantage of our method for handling the large-scale multi-view situation. |
| Tasks | |
| Published | 2017-07-18 |
| URL | http://arxiv.org/abs/1707.09866v1 |
| http://arxiv.org/pdf/1707.09866v1.pdf | |
| PWC | https://paperswithcode.com/paper/guided-co-training-for-large-scale-multi-view |
| Repo | |
| Framework | |
Deep Learning Interior Tomography for Region-of-Interest Reconstruction
| Title | Deep Learning Interior Tomography for Region-of-Interest Reconstruction |
| Authors | Yoseob Han, Jawook Gu, Jong Chul Ye |
| Abstract | Interior tomography for the region-of-interest (ROI) imaging has advantages of using a small detector and reducing X-ray radiation dose. However, standard analytic reconstruction suffers from severe cupping artifacts due to existence of null space in the truncated Radon transform. Existing penalized reconstruction methods may address this problem but they require extensive computations due to the iterative reconstruction. Inspired by the recent deep learning approaches to low-dose and sparse view CT, here we propose a deep learning architecture that removes null space signals from the FBP reconstruction. Experimental results have shown that the proposed method provides near-perfect reconstruction with about 7-10 dB improvement in PSNR over existing methods in spite of significantly reduced run-time complexity. |
| Tasks | |
| Published | 2017-12-29 |
| URL | http://arxiv.org/abs/1712.10248v2 |
| http://arxiv.org/pdf/1712.10248v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-interior-tomography-for-region |
| Repo | |
| Framework | |
Constraints, Lazy Constraints, or Propagators in ASP Solving: An Empirical Analysis
| Title | Constraints, Lazy Constraints, or Propagators in ASP Solving: An Empirical Analysis |
| Authors | Bernardo Cuteri, Carmine Dodaro, Francesco Ricca, Peter Schüller |
| Abstract | Answer Set Programming (ASP) is a well-established declarative paradigm. One of the successes of ASP is the availability of efficient systems. State-of-the-art systems are based on the ground+solve approach. In some applications this approach is infeasible because the grounding of one or few constraints is expensive. In this paper, we systematically compare alternative strategies to avoid the instantiation of problematic constraints, that are based on custom extensions of the solver. Results on real and synthetic benchmarks highlight some strengths and weaknesses of the different strategies. (Under consideration for acceptance in TPLP, ICLP 2017 Special Issue.) |
| Tasks | |
| Published | 2017-07-13 |
| URL | http://arxiv.org/abs/1707.04027v1 |
| http://arxiv.org/pdf/1707.04027v1.pdf | |
| PWC | https://paperswithcode.com/paper/constraints-lazy-constraints-or-propagators |
| Repo | |
| Framework | |
Improving Person Re-identification by Attribute and Identity Learning
| Title | Improving Person Re-identification by Attribute and Identity Learning |
| Authors | Yutian Lin, Liang Zheng, Zhedong Zheng, Yu Wu, Zhilan Hu, Chenggang Yan, Yi Yang |
| Abstract | Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into consideration. However, we find the attributes, containing detailed local descriptions, are beneficial in allowing the re-ID model to learn more discriminative feature representations. In this paper, based on the complementarity of attribute labels and ID labels, we propose an attribute-person recognition (APR) network, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes. We manually annotate attribute labels for two large-scale re-ID datasets, and systematically investigate how person re-ID and attribute recognition benefit from each other. In addition, we re-weight the attribute predictions considering the dependencies and correlations among the attributes. The experimental results on two large-scale re-ID benchmarks demonstrate that by learning a more discriminative representation, APR achieves competitive re-ID performance compared with the state-of-the-art methods. We use APR to speed up the retrieval process by ten times with a minor accuracy drop of 2.92% on Market-1501. Besides, we also apply APR on the attribute recognition task and demonstrate improvement over the baselines. |
| Tasks | Person Recognition, Person Re-Identification |
| Published | 2017-03-21 |
| URL | https://arxiv.org/abs/1703.07220v3 |
| https://arxiv.org/pdf/1703.07220v3.pdf | |
| PWC | https://paperswithcode.com/paper/improving-person-re-identification-by |
| Repo | |
| Framework | |
Neural Networks Architecture Evaluation in a Quantum Computer
| Title | Neural Networks Architecture Evaluation in a Quantum Computer |
| Authors | Adenilton José da Silva, Rodolfo Luan F. de Oliveira |
| Abstract | In this work, we propose a quantum algorithm to evaluate neural networks architectures named Quantum Neural Network Architecture Evaluation (QNNAE). The proposed algorithm is based on a quantum associative memory and the learning algorithm for artificial neural networks. Unlike conventional algorithms for evaluating neural network architectures, QNNAE does not depend on initialization of weights. The proposed algorithm has a binary output and results in 0 with probability proportional to the performance of the network. And its computational cost is equal to the computational cost to train a neural network. |
| Tasks | |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04759v1 |
| http://arxiv.org/pdf/1711.04759v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-architecture-evaluation-in-a |
| Repo | |
| Framework | |
Tikhonov Regularization for Long Short-Term Memory Networks
| Title | Tikhonov Regularization for Long Short-Term Memory Networks |
| Authors | Andrei Turkin |
| Abstract | It is a well-known fact that adding noise to the input data often improves network performance. While the dropout technique may be a cause of memory loss, when it is applied to recurrent connections, Tikhonov regularization, which can be regarded as the training with additive noise, avoids this issue naturally, though it implies regularizer derivation for different architectures. In case of feedforward neural networks this is straightforward, while for networks with recurrent connections and complicated layers it leads to some difficulties. In this paper, a Tikhonov regularizer is derived for Long-Short Term Memory (LSTM) networks. Although it is independent of time for simplicity, it considers interaction between weights of the LSTM unit, which in theory makes it possible to regularize the unit with complicated dependences by using only one parameter that measures the input data perturbation. The regularizer that is proposed in this paper has three parameters: one to control the regularization process, and other two to maintain computation stability while the network is being trained. The theory developed in this paper can be applied to get such regularizers for different recurrent neural networks with Hadamard products and Lipschitz continuous functions. |
| Tasks | |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.02979v1 |
| http://arxiv.org/pdf/1708.02979v1.pdf | |
| PWC | https://paperswithcode.com/paper/tikhonov-regularization-for-long-short-term |
| Repo | |
| Framework | |
Feature Enhancement in Visually Impaired Images
| Title | Feature Enhancement in Visually Impaired Images |
| Authors | Madhuri Suthar, Mohammad Asghari, Bahram Jalali |
| Abstract | One of the major open problems in computer vision is detection of features in visually impaired images. In this paper, we describe a potential solution using Phase Stretch Transform, a new computational approach for image analysis, edge detection and resolution enhancement that is inspired by the physics of the photonic time stretch technique. We mathematically derive the intrinsic nonlinear transfer function and demonstrate how it leads to (1) superior performance at low contrast levels and (2) a reconfigurable operator for hyper-dimensional classification. We prove that the Phase Stretch Transform equalizes the input image brightness across the range of intensities resulting in a high dynamic range in visually impaired images. We also show further improvement in the dynamic range by combining our method with the conventional techniques. Finally, our results show a method for computation of mathematical derivatives via group delay dispersion operations. |
| Tasks | Edge Detection |
| Published | 2017-06-14 |
| URL | http://arxiv.org/abs/1706.04671v1 |
| http://arxiv.org/pdf/1706.04671v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-enhancement-in-visually-impaired |
| Repo | |
| Framework | |
Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification
| Title | Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification |
| Authors | Nikolaos Sarafianos, Theodore Giannakopoulos, Christophoros Nikou, Ioannis A. Kakadiaris |
| Abstract | Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped after performing hierarchical clustering based on their correlation. The clusters of tasks are learned in a curriculum learning setup by transferring knowledge between clusters. The learning process within each cluster is performed in a multi-task classification setup. By leveraging the acquired knowledge, we speed-up the process and improve performance. We demonstrate the effectiveness of our method via ablation studies and a detailed analysis of the covariates, on a variety of publicly available datasets of humans standing with their full-body visible. Extensive experimentation has proven that the proposed approach boosts the performance by 4% to 10%. |
| Tasks | |
| Published | 2017-09-19 |
| URL | http://arxiv.org/abs/1709.06664v3 |
| http://arxiv.org/pdf/1709.06664v3.pdf | |
| PWC | https://paperswithcode.com/paper/curriculum-learning-of-visual-attribute |
| Repo | |
| Framework | |
Learning Conversational Systems that Interleave Task and Non-Task Content
| Title | Learning Conversational Systems that Interleave Task and Non-Task Content |
| Authors | Zhou Yu, Alan W Black, Alexander I. Rudnicky |
| Abstract | Task-oriented dialog systems have been applied in various tasks, such as automated personal assistants, customer service providers and tutors. These systems work well when users have clear and explicit intentions that are well-aligned to the systems’ capabilities. However, they fail if users intentions are not explicit. To address this shortcoming, we propose a framework to interleave non-task content (i.e. everyday social conversation) into task conversations. When the task content fails, the system can still keep the user engaged with the non-task content. We trained a policy using reinforcement learning algorithms to promote long-turn conversation coherence and consistency, so that the system can have smooth transitions between task and non-task content. To test the effectiveness of the proposed framework, we developed a movie promotion dialog system. Experiments with human users indicate that a system that interleaves social and task content achieves a better task success rate and is also rated as more engaging compared to a pure task-oriented system. |
| Tasks | |
| Published | 2017-03-01 |
| URL | http://arxiv.org/abs/1703.00099v1 |
| http://arxiv.org/pdf/1703.00099v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-conversational-systems-that |
| Repo | |
| Framework | |
A Watermarking Technique Using Discrete Curvelet Transform for Security of Multiple Biometric Features
| Title | A Watermarking Technique Using Discrete Curvelet Transform for Security of Multiple Biometric Features |
| Authors | Rohit M. Thanki, Ved Vyas Dwivedi, Komal R. Borisagar |
| Abstract | The robustness and security of the biometric watermarking approach can be improved by using a multiple watermarking. This multiple watermarking proposed for improving security of biometric features and data. When the imposter tries to create the spoofed biometric feature, the invisible biometric watermark features can provide appropriate protection to multimedia data. In this paper, a biometric watermarking technique with multiple biometric watermarks are proposed in which biometric features of fingerprint, face, iris and signature is embedded in the image. Before embedding, fingerprint, iris, face and signature features are extracted using Shen-Castan edge detection and Principal Component Analysis. These all biometric watermark features are embedded into various mid band frequency curvelet coefficients of host image. All four fingerprint features, iris features, facial features and signature features are the biometric characteristics of the individual and they are used for cross verification and copyright protection if any manipulation occurs. The proposed technique is fragile enough; features cannot be extracted from the watermarked image when an imposter tries to remove watermark features illegally. It can use for multiple copyright authentication and verification. |
| Tasks | Edge Detection |
| Published | 2017-01-16 |
| URL | http://arxiv.org/abs/1701.04185v1 |
| http://arxiv.org/pdf/1701.04185v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-watermarking-technique-using-discrete |
| Repo | |
| Framework | |
Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo
| Title | Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo |
| Authors | Paschalis Panteleris, Antonis Argyros |
| Abstract | We present a novel solution to the problem of 3D tracking of the articulated motion of human hand(s), possibly in interaction with other objects. The vast majority of contemporary relevant work capitalizes on depth information provided by RGBD cameras. In this work, we show that accurate and efficient 3D hand tracking is possible, even for the case of RGB stereo. A straightforward approach for solving the problem based on such input would be to first recover depth and then apply a state of the art depth-based 3D hand tracking method. Unfortunately, this does not work well in practice because the stereo-based, dense 3D reconstruction of hands is far less accurate than the one obtained by RGBD cameras. Our approach bypasses 3D reconstruction and follows a completely different route: 3D hand tracking is formulated as an optimization problem whose solution is the hand configuration that maximizes the color consistency between the two views of the hand. We demonstrate the applicability of our method for real time tracking of a single hand, of a hand manipulating an object and of two interacting hands. The method has been evaluated quantitatively on standard datasets and in comparison to relevant, state of the art RGBD-based approaches. The obtained results demonstrate that the proposed stereo-based method performs equally well to its RGBD-based competitors, and in some cases, it even outperforms them. |
| Tasks | 3D Reconstruction |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05301v1 |
| http://arxiv.org/pdf/1705.05301v1.pdf | |
| PWC | https://paperswithcode.com/paper/back-to-rgb-3d-tracking-of-hands-and-hand |
| Repo | |
| Framework | |
Inductive Pairwise Ranking: Going Beyond the n log(n) Barrier
| Title | Inductive Pairwise Ranking: Going Beyond the n log(n) Barrier |
| Authors | U. N. Niranjan, Arun Rajkumar |
| Abstract | We study the problem of ranking a set of items from nonactively chosen pairwise preferences where each item has feature information with it. We propose and characterize a very broad class of preference matrices giving rise to the Feature Low Rank (FLR) model, which subsumes several models ranging from the classic Bradley-Terry-Luce (BTL) (Bradley and Terry 1952) and Thurstone (Thurstone 1927) models to the recently proposed blade-chest (Chen and Joachims 2016) and generic low-rank preference (Rajkumar and Agarwal 2016) models. We use the technique of matrix completion in the presence of side information to develop the Inductive Pairwise Ranking (IPR) algorithm that provably learns a good ranking under the FLR model, in a sample-efficient manner. In practice, through systematic synthetic simulations, we confirm our theoretical findings regarding improvements in the sample complexity due to the use of feature information. Moreover, on popular real-world preference learning datasets, with as less as 10% sampling of the pairwise comparisons, our method recovers a good ranking. |
| Tasks | Matrix Completion |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02661v1 |
| http://arxiv.org/pdf/1702.02661v1.pdf | |
| PWC | https://paperswithcode.com/paper/inductive-pairwise-ranking-going-beyond-the-n |
| Repo | |
| Framework | |
A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI
| Title | A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI |
| Authors | Justin Domke |
| Abstract | Two popular classes of methods for approximate inference are Markov chain Monte Carlo (MCMC) and variational inference. MCMC tends to be accurate if run for a long enough time, while variational inference tends to give better approximations at shorter time horizons. However, the amount of time needed for MCMC to exceed the performance of variational methods can be quite high, motivating more fine-grained tradeoffs. This paper derives a distribution over variational parameters, designed to minimize a bound on the divergence between the resulting marginal distribution and the target, and gives an example of how to sample from this distribution in a way that interpolates between the behavior of existing methods based on Langevin dynamics and stochastic gradient variational inference (SGVI). |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06529v1 |
| http://arxiv.org/pdf/1706.06529v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-divergence-bound-for-hybrids-of-mcmc-and |
| Repo | |
| Framework | |
