Paper Group ANR 149
Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition. Latent Dirichlet Allocation with Residual Convolutional Neural Network Applied in Evaluating Credibility of Chinese Listed Companies. An Outcome Model Approach to Translating a Randomized Controlled Trial Results to a Target Population. Tensor Alignment Bas …
Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition
Title | Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition |
Authors | Shenglan Liu, Shuai Guo, Hong Qiao, Yang Wang, Bin Wang, Wenbo Luo, Mingming Zhang, Keye Zhang, Bixuan Du |
Abstract | Human emotion recognition is an important direction in the field of biometric and information forensics. However, most existing human emotion research are based on the single RGB view. In this paper, we introduce a RGBD video-emotion dataset and a RGBD face-emotion dataset for research. To our best knowledge, this may be the first RGBD video-emotion dataset. We propose a new supervised nonlinear multi-view laplacian eigenmaps (MvLE) approach and a multihidden-layer out-of-sample network (MHON) for RGB-D humanemotion recognition. To get better representations of RGB view and depth view, MvLE is used to map the training set of both views from original space into the common subspace. As RGB view and depth view lie in different spaces, a new distance metric bag of neighbors (BON) used in MvLE can get the similar distributions of the two views. Finally, MHON is used to get the low-dimensional representations of test data and predict their labels. MvLE can deal with the cases that RGB view and depth view have different size of features, even different number of samples and classes. And our methods can be easily extended to more than two views. The experiment results indicate the effectiveness of our methods over some state-of-art methods. |
Tasks | Emotion Recognition |
Published | 2018-11-08 |
URL | http://arxiv.org/abs/1811.03478v1 |
http://arxiv.org/pdf/1811.03478v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-view-laplacian-eigenmaps-based-on-bag |
Repo | |
Framework | |
Latent Dirichlet Allocation with Residual Convolutional Neural Network Applied in Evaluating Credibility of Chinese Listed Companies
Title | Latent Dirichlet Allocation with Residual Convolutional Neural Network Applied in Evaluating Credibility of Chinese Listed Companies |
Authors | Mohan Zhang, Zhichao Luo, Hai Lu |
Abstract | This project demonstrated a methodology to estimating cooperate credibility with a Natural Language Processing approach. As cooperate transparency impacts both the credibility and possible future earnings of the firm, it is an important factor to be considered by banks and investors on risk assessments of listed firms. This approach of estimating cooperate credibility can bypass human bias and inconsistency in the risk assessment, the use of large quantitative data and neural network models provides more accurate estimation in a more efficient manner compare to manual assessment. At the beginning, the model will employs Latent Dirichlet Allocation and THU Open Chinese Lexicon from Tsinghua University to classify topics in articles which are potentially related to corporate credibility. Then with the keywords related to each topics, we trained a residual convolutional neural network with data labeled according to surveys of fund manager and accountant’s opinion on corporate credibility. After the training, we run the model with preprocessed news reports regarding to all of the 3065 listed companies, the model is supposed to give back companies ranking based on the level of their transparency. |
Tasks | |
Published | 2018-11-24 |
URL | http://arxiv.org/abs/1811.11017v1 |
http://arxiv.org/pdf/1811.11017v1.pdf | |
PWC | https://paperswithcode.com/paper/latent-dirichlet-allocation-with-residual |
Repo | |
Framework | |
An Outcome Model Approach to Translating a Randomized Controlled Trial Results to a Target Population
Title | An Outcome Model Approach to Translating a Randomized Controlled Trial Results to a Target Population |
Authors | Benjamin A. Goldstein, Matthew Phelan, Neha J. Pagidipati, Rury R. Holman, Michael J. Pencina Elizabeth A Stuart |
Abstract | Participants enrolled into randomized controlled trials (RCTs) often do not reflect real-world populations. Previous research in how best to translate RCT results to target populations has focused on weighting RCT data to look like the target data. Simulation work, however, has suggested that an outcome model approach may be preferable. Here we describe such an approach using source data from the 2x2 factorial NAVIGATOR trial which evaluated the impact of valsartan and nateglinide on cardiovascular outcomes and new-onset diabetes in a pre-diabetic population. Our target data consisted of people with pre-diabetes serviced at our institution. We used Random Survival Forests to develop separate outcome models for each of the 4 treatments, estimating the 5-year risk difference for progression to diabetes and estimated the treatment effect in our local patient populations, as well as sub-populations, and the results compared to the traditional weighting approach. Our models suggested that the treatment effect for valsartan in our patient population was the same as in the trial, whereas for nateglinide treatment effect was stronger than observed in the original trial. Our effect estimates were more efficient than the weighting approach. |
Tasks | |
Published | 2018-06-25 |
URL | http://arxiv.org/abs/1806.09692v1 |
http://arxiv.org/pdf/1806.09692v1.pdf | |
PWC | https://paperswithcode.com/paper/an-outcome-model-approach-to-translating-a |
Repo | |
Framework | |
Tensor Alignment Based Domain Adaptation for Hyperspectral Image Classification
Title | Tensor Alignment Based Domain Adaptation for Hyperspectral Image Classification |
Authors | Yao Qin, Lorenzo Bruzzone, Biao Li |
Abstract | This paper presents a tensor alignment (TA) based domain adaptation method for hyperspectral image (HSI) classification. To be specific, HSIs in both domains are first segmented into superpixels and tensors of both domains are constructed to include neighboring samples from single superpixel. Then we consider the subspace invariance between two domains as projection matrices and original tensors are projected as core tensors with lower dimensions into the invariant tensor subspace by applying Tucker decomposition. To preserve geometric information in original tensors, we employ a manifold regularization term for core tensors into the decomposition progress. The projection matrices and core tensors are solved in an alternating optimization manner and the convergence of TA algorithm is analyzed. In addition, a post-processing strategy is defined via pure samples extraction for each superpixel to further improve classification performance. Experimental results on four real HSIs demonstrate that the proposed method can achieve better performance compared with the state-of-the-art subspace learning methods when a limited amount of source labeled samples are available. |
Tasks | Domain Adaptation, Hyperspectral Image Classification, Image Classification |
Published | 2018-08-29 |
URL | http://arxiv.org/abs/1808.09769v2 |
http://arxiv.org/pdf/1808.09769v2.pdf | |
PWC | https://paperswithcode.com/paper/tensor-alignment-based-domain-adaptation-for |
Repo | |
Framework | |
A Smoke Removal Method for Laparoscopic Images
Title | A Smoke Removal Method for Laparoscopic Images |
Authors | Congcong Wang, Faouzi Alaya Cheikh, Mounir Kaaniche, Ole Jacob Elle |
Abstract | In laparoscopic surgery, image quality can be severely degraded by surgical smoke, which not only introduces error for the image processing (used in image guided surgery), but also reduces the visibility of the surgeons. In this paper, we propose to enhance the laparoscopic images by decomposing them into unwanted smoke part and enhanced part using a variational approach. The proposed method relies on the observation that smoke has low contrast and low inter-channel differences. A cost function is defined based on this prior knowledge and is solved using an augmented Lagrangian method. The obtained unwanted smoke component is then subtracted from the original degraded image, resulting in the enhanced image. The obtained quantitative scores in terms of FADE, JNBM and RE metrics show that our proposed method performs rather well. Furthermore, the qualitative visual inspection of the results show that it removes smoke effectively from the laparoscopic images. |
Tasks | |
Published | 2018-03-22 |
URL | http://arxiv.org/abs/1803.08410v1 |
http://arxiv.org/pdf/1803.08410v1.pdf | |
PWC | https://paperswithcode.com/paper/a-smoke-removal-method-for-laparoscopic |
Repo | |
Framework | |
Beta Distribution Drift Detection for Adaptive Classifiers
Title | Beta Distribution Drift Detection for Adaptive Classifiers |
Authors | Lukas Fleckenstein, Sebastian Kauschke, Johannes Fürnkranz |
Abstract | With today’s abundant streams of data, the only constant we can rely on is change. For stream classification algorithms, it is necessary to adapt to concept drift. This can be achieved by monitoring the model error, and triggering counter measures as changes occur. In this paper, we propose a drift detection mechanism that fits a beta distribution to the model error, and treats abnormal behavior as drift. It works with any given model, leverages prior knowledge about this model, and allows to set application-specific confidence thresholds. Experiments confirm that it performs well, in particular when drift occurs abruptly. |
Tasks | |
Published | 2018-11-27 |
URL | http://arxiv.org/abs/1811.10900v1 |
http://arxiv.org/pdf/1811.10900v1.pdf | |
PWC | https://paperswithcode.com/paper/beta-distribution-drift-detection-for |
Repo | |
Framework | |
MR-GAN: Manifold Regularized Generative Adversarial Networks
Title | MR-GAN: Manifold Regularized Generative Adversarial Networks |
Authors | Qunwei Li, Bhavya Kailkhura, Rushil Anirudh, Yi Zhou, Yingbin Liang, Pramod Varshney |
Abstract | Despite the growing interest in generative adversarial networks (GANs), training GANs remains a challenging problem, both from a theoretical and a practical standpoint. To address this challenge, in this paper, we propose a novel way to exploit the unique geometry of the real data, especially the manifold information. More specifically, we design a method to regularize GAN training by adding an additional regularization term referred to as manifold regularizer. The manifold regularizer forces the generator to respect the unique geometry of the real data manifold and generate high quality data. Furthermore, we theoretically prove that the addition of this regularization term in any class of GANs including DCGAN and Wasserstein GAN leads to improved performance in terms of generalization, existence of equilibrium, and stability. Preliminary experiments show that the proposed manifold regularization helps in avoiding mode collapse and leads to stable training. |
Tasks | |
Published | 2018-11-22 |
URL | http://arxiv.org/abs/1811.10427v1 |
http://arxiv.org/pdf/1811.10427v1.pdf | |
PWC | https://paperswithcode.com/paper/mr-gan-manifold-regularized-generative |
Repo | |
Framework | |
Deeply-Sparse Signal rePresentations ($\text{D}\text{S}^2\text{P}$)
Title | Deeply-Sparse Signal rePresentations ($\text{D}\text{S}^2\text{P}$) |
Authors | Demba Ba |
Abstract | A recent line of work has sought to build a parallel between deep neural network architectures and sparse coding/recovery and estimation. Said line of work suggests, as pointed out by Papyan et al., that a deep neural network architecture with ReLu nonlinearities arises from a finite sequence of cascaded sparse coding models, the outputs of which, except for the last element in the cascade, are sparse and unobservable. That is, intermediate outputs deep in the cascade are sparse, hence the title of this manuscript. We show here, using techniques from the dictionary learning/sparse coding literature, that if the measurement matrices in the cascaded sparse coding model (a) satisfy RIP and (b) all have sparse columns except for the last, they can be recovered with high probability in the absence of noise using an optimization algorithm that, beginning with the last element of the cascade, alternates between estimating the dictionary and the sparse code and then, at convergence, proceeds to the preceding element in the cascade. The method of choice in deep learning to solve this problem is by training an auto-encoder whose architecture we specify. Our algorithm provides a sound alternative, derived from the perspective of sparse coding, and with theoretical guarantees, as well as sample complexity assessments. In particular, the learning complexity depends on the maximum, across layers, of the product of the number of active neurons and the embedding dimension. Our proof relies on a certain type of sparse random matrix satisfying the RIP property. We use non-asymptotic random matrix theory to prove this. We demonstrate the deep dictionary learning algorithm via simulation. |
Tasks | Dictionary Learning |
Published | 2018-07-05 |
URL | https://arxiv.org/abs/1807.01958v4 |
https://arxiv.org/pdf/1807.01958v4.pdf | |
PWC | https://paperswithcode.com/paper/deeply-sparse-signal-representations |
Repo | |
Framework | |
Study of Set-Membership Adaptive Kernel Algorithms
Title | Study of Set-Membership Adaptive Kernel Algorithms |
Authors | A. Flores, R. C. de Lamare |
Abstract | In the last decade, a considerable research effort has been devoted to developing adaptive algorithms based on kernel functions. One of the main features of these algorithms is that they form a family of universal approximation techniques, solving problems with nonlinearities elegantly. In this paper, we present data-selective adaptive kernel normalized least-mean square (KNLMS) algorithms that can increase their learning rate and reduce their computational complexity. In fact, these methods deal with kernel expansions, creating a growing structure also known as the dictionary, whose size depends on the number of observations and their innovation. The algorithms described herein use an adaptive step-size to accelerate the learning and can offer an excellent tradeoff between convergence speed and steady state, which allows them to solve nonlinear filtering and estimation problems with a large number of parameters without requiring a large computational cost. The data-selective update scheme also limits the number of operations performed and the size of the dictionary created by the kernel expansion, saving computational resources and dealing with one of the major problems of kernel adaptive algorithms. A statistical analysis is carried out along with a computational complexity analysis of the proposed algorithms. Simulations show that the proposed KNLMS algorithms outperform existing algorithms in examples of nonlinear system identification and prediction of a time series originating from a nonlinear difference equation. |
Tasks | Time Series |
Published | 2018-08-15 |
URL | http://arxiv.org/abs/1808.06536v1 |
http://arxiv.org/pdf/1808.06536v1.pdf | |
PWC | https://paperswithcode.com/paper/study-of-set-membership-adaptive-kernel |
Repo | |
Framework | |
Btrfly Net: Vertebrae Labelling with Energy-based Adversarial Learning of Local Spine Prior
Title | Btrfly Net: Vertebrae Labelling with Energy-based Adversarial Learning of Local Spine Prior |
Authors | Anjany Sekuboyina, Markus Rempfler, Jan Kukačka, Giles Tetteh, Alexander Valentinitsch, Jan S. Kirschke, Bjoern H. Menze |
Abstract | Robust localisation and identification of vertebrae is essential for automated spine analysis. The contribution of this work to the task is two-fold: (1) Inspired by the human expert, we hypothesise that a sagittal and coronal reformation of the spine contain sufficient information for labelling the vertebrae. Thereby, we propose a butterfly-shaped network architecture (termed Btrfly Net) that efficiently combines the information across reformations. (2) Underpinning the Btrfly net, we present an energy-based adversarial training regime that encodes local spine structure as an anatomical prior into the network, thereby enabling it to achieve state-of-art performance in all standard metrics on a benchmark dataset of 302 scans without any post-processing during inference. |
Tasks | |
Published | 2018-04-04 |
URL | http://arxiv.org/abs/1804.01307v2 |
http://arxiv.org/pdf/1804.01307v2.pdf | |
PWC | https://paperswithcode.com/paper/btrfly-net-vertebrae-labelling-with-energy |
Repo | |
Framework | |
Bandits with Side Observations: Bounded vs. Logarithmic Regret
Title | Bandits with Side Observations: Bounded vs. Logarithmic Regret |
Authors | Rémy Degenne, Evrard Garcelon, Vianney Perchet |
Abstract | We consider the classical stochastic multi-armed bandit but where, from time to time and roughly with frequency $\epsilon$, an extra observation is gathered by the agent for free. We prove that, no matter how small $\epsilon$ is the agent can ensure a regret uniformly bounded in time. More precisely, we construct an algorithm with a regret smaller than $\sum_i \frac{\log(1/\epsilon)}{\Delta_i}$, up to multiplicative constant and loglog terms. We also prove a matching lower-bound, stating that no reasonable algorithm can outperform this quantity. |
Tasks | |
Published | 2018-07-10 |
URL | http://arxiv.org/abs/1807.03558v1 |
http://arxiv.org/pdf/1807.03558v1.pdf | |
PWC | https://paperswithcode.com/paper/bandits-with-side-observations-bounded-vs |
Repo | |
Framework | |
Multi-Output Gaussian Processes for Crowdsourced Traffic Data Imputation
Title | Multi-Output Gaussian Processes for Crowdsourced Traffic Data Imputation |
Authors | Filipe Rodrigues, Kristian Henrickson, Francisco C. Pereira |
Abstract | Traffic speed data imputation is a fundamental challenge for data-driven transport analysis. In recent years, with the ubiquity of GPS-enabled devices and the widespread use of crowdsourcing alternatives for the collection of traffic data, transportation professionals increasingly look to such user-generated data for many analysis, planning, and decision support applications. However, due to the mechanics of the data collection process, crowdsourced traffic data such as probe-vehicle data is highly prone to missing observations, making accurate imputation crucial for the success of any application that makes use of that type of data. In this article, we propose the use of multi-output Gaussian processes (GPs) to model the complex spatial and temporal patterns in crowdsourced traffic data. While the Bayesian nonparametric formalism of GPs allows us to model observation uncertainty, the multi-output extension based on convolution processes effectively enables us to capture complex spatial dependencies between nearby road segments. Using 6 months of crowdsourced traffic speed data or “probe vehicle data” for several locations in Copenhagen, the proposed approach is empirically shown to significantly outperform popular state-of-the-art imputation methods. |
Tasks | Gaussian Processes, Imputation, Traffic Data Imputation, Traffic Prediction |
Published | 2018-12-20 |
URL | https://arxiv.org/abs/1812.08739v2 |
https://arxiv.org/pdf/1812.08739v2.pdf | |
PWC | https://paperswithcode.com/paper/multi-output-gaussian-processes-for |
Repo | |
Framework | |
Neuroimaging Modality Fusion in Alzheimer’s Classification Using Convolutional Neural Networks
Title | Neuroimaging Modality Fusion in Alzheimer’s Classification Using Convolutional Neural Networks |
Authors | Arjun Punjabi, Adam Martersteck, Yanran Wang, Todd B. Parrish, Aggelos K. Katsaggelos, the Alzheimer’s Disease Neuroimaging Initiative |
Abstract | Automated methods for Alzheimer’s disease (AD) classification have the potential for great clinical benefits and may provide insight for combating the disease. Machine learning, and more specifically deep neural networks, have been shown to have great efficacy in this domain. These algorithms often use neurological imaging data such as MRI and PET, but a comprehensive and balanced comparison of these modalities has not been performed. In order to accurately determine the relative strength of each imaging variant, this work performs a comparison study in the context of Alzheimer’s dementia classification using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. Furthermore, this work analyzes the benefits of using both modalities in a fusion setting and discusses how these data types may be leveraged in future AD studies using deep learning. |
Tasks | |
Published | 2018-11-13 |
URL | http://arxiv.org/abs/1811.05105v1 |
http://arxiv.org/pdf/1811.05105v1.pdf | |
PWC | https://paperswithcode.com/paper/neuroimaging-modality-fusion-in-alzheimers |
Repo | |
Framework | |
Word2Vec applied to Recommendation: Hyperparameters Matter
Title | Word2Vec applied to Recommendation: Hyperparameters Matter |
Authors | Hugo Caselles-Dupré, Florian Lesaint, Jimena Royo-Letelier |
Abstract | Skip-gram with negative sampling, a popular variant of Word2vec originally designed and tuned to create word embeddings for Natural Language Processing, has been used to create item embeddings with successful applications in recommendation. While these fields do not share the same type of data, neither evaluate on the same tasks, recommendation applications tend to use the same already tuned hyperparameters values, even if optimal hyperparameters values are often known to be data and task dependent. We thus investigate the marginal importance of each hyperparameter in a recommendation setting through large hyperparameter grid searches on various datasets. Results reveal that optimizing neglected hyperparameters, namely negative sampling distribution, number of epochs, subsampling parameter and window-size, significantly improves performance on a recommendation task, and can increase it by an order of magnitude. Importantly, we find that optimal hyperparameters configurations for Natural Language Processing tasks and Recommendation tasks are noticeably different. |
Tasks | Word Embeddings |
Published | 2018-04-11 |
URL | http://arxiv.org/abs/1804.04212v3 |
http://arxiv.org/pdf/1804.04212v3.pdf | |
PWC | https://paperswithcode.com/paper/word2vec-applied-to-recommendation |
Repo | |
Framework | |
Design Flow of Accelerating Hybrid Extremely Low Bit-width Neural Network in Embedded FPGA
Title | Design Flow of Accelerating Hybrid Extremely Low Bit-width Neural Network in Embedded FPGA |
Authors | Junsong Wang, Qiuwen Lou, Xiaofan Zhang, Chao Zhu, Yonghua Lin, Deming Chen |
Abstract | Neural network accelerators with low latency and low energy consumption are desirable for edge computing. To create such accelerators, we propose a design flow for accelerating the extremely low bit-width neural network (ELB-NN) in embedded FPGAs with hybrid quantization schemes. This flow covers both network training and FPGA-based network deployment, which facilitates the design space exploration and simplifies the tradeoff between network accuracy and computation efficiency. Using this flow helps hardware designers to deliver a network accelerator in edge devices under strict resource and power constraints. We present the proposed flow by supporting hybrid ELB settings within a neural network. Results show that our design can deliver very high performance peaking at 10.3 TOPS and classify up to 325.3 image/s/watt while running large-scale neural networks for less than 5W using embedded FPGA. To the best of our knowledge, it is the most energy efficient solution in comparison to GPU or other FPGA implementations reported so far in the literature. |
Tasks | Quantization |
Published | 2018-07-31 |
URL | http://arxiv.org/abs/1808.04311v2 |
http://arxiv.org/pdf/1808.04311v2.pdf | |
PWC | https://paperswithcode.com/paper/design-flow-of-accelerating-hybrid-extremely |
Repo | |
Framework | |