October 17, 2019

2982 words 14 mins read

Paper Group ANR 957

Noise Sensitivity of Local Descriptors vs ConvNets: An application to Facial Recognition. Wavelet Sparse Regularization for Manifold-Valued Data. Arbitrary Discrete Sequence Anomaly Detection with Zero Boundary LSTM. Can we learn where people go?. Proximal Policy Optimization and its Dynamic Version for Sequence Generation. Deep Unfolded Robust PCA …

Noise Sensitivity of Local Descriptors vs ConvNets: An application to Facial Recognition


Title	Noise Sensitivity of Local Descriptors vs ConvNets: An application to Facial Recognition
Authors	Yasin Musa Ayami, Aboubayda Shabat, Delene Heukelman
Abstract	The Local Binary Patterns (LBP) is a local descriptor proposed by Ojala et al to discriminate texture due to its discriminative power. However, the LBP is sensitive to noise and illumination changes. Consequently, several extensions to the LBP such as Median Binary Pattern (MBP) and methods such as Local Directional Pattern (LDP) have been proposed to address its drawbacks. Though studies by Zhou et al, suggest that the LDP exhibits poor performance in presence of random noise. Recently, convolution neural networks (ConvNets) were introduced which are increasingly becoming popular for feature extraction due to their discriminative power. This study aimed at evaluating the sensitivity of ResNet50, a ConvNet pre-trained model and local descriptors (LBP and LDP) to noise using the Extended Yale B face dataset with 5 different levels of noise added to the dataset. In our findings, it was observed that despite adding different levels of noise to the dataset, ResNet50 proved to be more robust than the local descriptors (LBP and LDP).
Tasks
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11515v1
PDF	http://arxiv.org/pdf/1810.11515v1.pdf
PWC	https://paperswithcode.com/paper/noise-sensitivity-of-local-descriptors-vs
Repo
Framework

Wavelet Sparse Regularization for Manifold-Valued Data


Title	Wavelet Sparse Regularization for Manifold-Valued Data
Authors	Martin Storath, Andreas Weinmann
Abstract	In this paper, we consider the sparse regularization of manifold-valued data with respect to an interpolatory wavelet/multiscale transform. We propose and study variational models for this task and provide results on their well-posedness. We present algorithms for a numerical realization of these models in the manifold setup. Further, we provide experimental results to show the potential of the proposed schemes for applications.
Tasks
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00505v1
PDF	http://arxiv.org/pdf/1808.00505v1.pdf
PWC	https://paperswithcode.com/paper/wavelet-sparse-regularization-for-manifold
Repo
Framework

Arbitrary Discrete Sequence Anomaly Detection with Zero Boundary LSTM


Title	Arbitrary Discrete Sequence Anomaly Detection with Zero Boundary LSTM
Authors	Chase Roberts, Manish Nair
Abstract	We propose a simple mathematical definition and new neural architecture for finding anomalies within discrete sequence datasets. Our model comprises of a modified LSTM autoencoder and an array of One-Class SVMs. The LSTM takes in elements from a sequence and creates context vectors that are used to predict the probability distribution of the following element. These context vectors are then used to train an array of One-Class SVMs. These SVMs are used to determine an outlier boundary in context space.We show that our method is consistently more stable and also outperforms standard LSTM and sliding window anomaly detection systems on two generated datasets.
Tasks	Anomaly Detection
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02395v1
PDF	http://arxiv.org/pdf/1803.02395v1.pdf
PWC	https://paperswithcode.com/paper/arbitrary-discrete-sequence-anomaly-detection
Repo
Framework

Can we learn where people go?


Title	Can we learn where people go?
Authors	Marion Gödel, Gerta Köster, Daniel Lehmberg, Manfred Gruber, Angelika Kneidl, Florian Sesser
Abstract	In most agent-based simulators, pedestrians navigate from origins to destinations. Consequently, destinations are essential input parameters to the simulation. While many other relevant parameters as positions, speeds and densities can be obtained from sensors, like cameras, destinations cannot be observed directly. Our research question is: Can we obtain this information from video data using machine learning methods? We use density heatmaps, which indicate the pedestrian density within a given camera cutout, as input to predict the destination distributions. For our proof of concept, we train a Random Forest predictor on an exemplary data set generated with the Vadere microscopic simulator. The scenario is a crossroad where pedestrians can head left, straight or right. In addition, we gain first insights on suitable placement of the camera. The results motivate an in-depth analysis of the methodology.
Tasks
Published	2018-12-10
URL	http://arxiv.org/abs/1812.03719v2
PDF	http://arxiv.org/pdf/1812.03719v2.pdf
PWC	https://paperswithcode.com/paper/can-we-learn-where-people-go
Repo
Framework

Proximal Policy Optimization and its Dynamic Version for Sequence Generation


Title	Proximal Policy Optimization and its Dynamic Version for Sequence Generation
Authors	Yi-Lin Tuan, Jinzhi Zhang, Yujia Li, Hung-yi Lee
Abstract	In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial learning. In this paper, we replace policy gradient with proximal policy optimization (PPO), which is a proved more efficient reinforcement learning algorithm, and propose a dynamic approach for PPO (PPO-dynamic). We demonstrate the efficacy of PPO and PPO-dynamic on conditional sequence generation tasks including synthetic experiment and chit-chat chatbot. The results show that PPO and PPO-dynamic can beat policy gradient by stability and performance.
Tasks	Chatbot
Published	2018-08-24
URL	http://arxiv.org/abs/1808.07982v1
PDF	http://arxiv.org/pdf/1808.07982v1.pdf
PWC	https://paperswithcode.com/paper/proximal-policy-optimization-and-its-dynamic
Repo
Framework

Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound


Title	Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound
Authors	Oren Solomon, Regev Cohen, Yi Zhang, Yi Yang, He Qiong, Jianwen Luo, Ruud J. G. van Sloun, Yonina C. Eldar
Abstract	Contrast enhanced ultrasound is a radiation-free imaging modality which uses encapsulated gas microbubbles for improved visualization of the vascular bed deep within the tissue. It has recently been used to enable imaging with unprecedented subwavelength spatial resolution by relying on super-resolution techniques. A typical preprocessing step in super-resolution ultrasound is to separate the microbubble signal from the cluttering tissue signal. This step has a crucial impact on the final image quality. Here, we propose a new approach to clutter removal based on robust principle component analysis (PCA) and deep learning. We begin by modeling the acquired contrast enhanced ultrasound signal as a combination of a low rank and sparse components. This model is used in robust PCA and was previously suggested in the context of ultrasound Doppler processing and dynamic magnetic resonance imaging. We then illustrate that an iterative algorithm based on this model exhibits improved separation of microbubble signal from the tissue signal over commonly practiced methods. Next, we apply the concept of deep unfolding to suggest a deep network architecture tailored to our clutter filtering problem which exhibits improved convergence speed and accuracy with respect to its iterative counterpart. We compare the performance of the suggested deep network on both simulations and in-vivo rat brain scans, with a commonly practiced deep-network architecture and the fast iterative shrinkage algorithm, and show that our architecture exhibits better image quality and contrast.
Tasks	Super-Resolution
Published	2018-11-20
URL	http://arxiv.org/abs/1811.08252v1
PDF	http://arxiv.org/pdf/1811.08252v1.pdf
PWC	https://paperswithcode.com/paper/deep-unfolded-robust-pca-with-application-to
Repo
Framework

Learning Finer-class Networks for Universal Representations


Title	Learning Finer-class Networks for Universal Representations
Authors	Julien Girard, Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot
Abstract	Many real-world visual recognition use-cases can not directly benefit from state-of-the-art CNN-based approaches because of the lack of many annotated data. The usual approach to deal with this is to transfer a representation pre-learned on a large annotated source-task onto a target-task of interest. This raises the question of how well the original representation is “universal”, that is to say directly adapted to many different target-tasks. To improve such universality, the state-of-the-art consists in training networks on a diversified source problem, that is modified either by adding generic or specific categories to the initial set of categories. In this vein, we proposed a method that exploits finer-classes than the most specific ones existing, for which no annotation is available. We rely on unsupervised learning and a bottom-up split and merge strategy. We show that our method learns more universal representations than state-of-the-art, leading to significantly better results on 10 target-tasks from multiple domains, using several network architectures, either alone or combined with networks learned at a coarser semantic level.
Tasks
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02126v1
PDF	http://arxiv.org/pdf/1810.02126v1.pdf
PWC	https://paperswithcode.com/paper/learning-finer-class-networks-for-universal
Repo
Framework

Learning Deep Representations from Clinical Data for Chronic Kidney Disease


Title	Learning Deep Representations from Clinical Data for Chronic Kidney Disease
Authors	Duc Thanh Anh Luong, Varun Chandola
Abstract	We study the behavior of a Time-Aware Long Short-Term Memory Autoencoder, a state-of-the-art method, in the context of learning latent representations from irregularly sampled patient data. We identify a key issue in the way such recurrent neural network models are being currently used and show that the solution of the issue leads to significant improvements in the learnt representations on both synthetic and real datasets. A detailed analysis of the improved methodology for representing patients suffering from Chronic Kidney Disease (CKD) using clinical data is provided. Experimental results show that the proposed T-LSTM model is able to capture the long-term trends in the data, while effectively handling the noise in the signal. Finally, we show that by using the latent representations of the CKD patients obtained from the T-LSTM autoencoder, one can identify unusual patient profiles from the target population.
Tasks	Time Series
Published	2018-10-01
URL	http://arxiv.org/abs/1810.00490v2
PDF	http://arxiv.org/pdf/1810.00490v2.pdf
PWC	https://paperswithcode.com/paper/learning-deep-representations-from-clinical
Repo
Framework

Variational 3D-PIV with Sparse Descriptors


Title	Variational 3D-PIV with Sparse Descriptors
Authors	Katrin Lasinger, Christoph Vogel, Thomas Pock, Konrad Schindler
Abstract	3D Particle Imaging Velocimetry (3D-PIV) aim to recover the flow field in a volume of fluid, which has been seeded with tracer particles and observed from multiple camera viewpoints. The first step of 3D-PIV is to reconstruct the 3D locations of the tracer particles from synchronous views of the volume. We propose a new method for iterative particle reconstruction (IPR), in which the locations and intensities of all particles are inferred in one joint energy minimization. The energy function is designed to penalize deviations between the reconstructed 3D particles and the image evidence, while at the same time aiming for a sparse set of particles. We find that the new method, without any post-processing, achieves significantly cleaner particle volumes than a conventional, tomographic MART reconstruction, and can handle a wide range of particle densities. The second step of 3D-PIV is to then recover the dense motion field from two consecutive particle reconstructions. We propose a variational model, which makes it possible to directly include physical properties, such as incompressibility and viscosity, in the estimation of the motion field. To further exploit the sparse nature of the input data, we propose a novel, compact descriptor of the local particle layout. Hence, we avoid the memory-intensive storage of high-resolution intensity volumes. Our framework is generic and allows for a variety of different data costs (correlation measures) and regularizers. We quantitatively evaluate it with both the sum of squared differences (SSD) and the normalized cross-correlation (NCC), respectively with both a hard and a soft version of the incompressibility constraint.
Tasks
Published	2018-04-09
URL	http://arxiv.org/abs/1804.02872v1
PDF	http://arxiv.org/pdf/1804.02872v1.pdf
PWC	https://paperswithcode.com/paper/variational-3d-piv-with-sparse-descriptors
Repo
Framework

Attentional Multi-Reading Sarcasm Detection


Title	Attentional Multi-Reading Sarcasm Detection
Authors	Reza Ghaeini, Xiaoli Z. Fern, Prasad Tadepalli
Abstract	Recognizing sarcasm often requires a deep understanding of multiple sources of information, including the utterance, the conversational context, and real world facts. Most of the current sarcasm detection systems consider only the utterance in isolation. There are some limited attempts toward taking into account the conversational context. In this paper, we propose an interpretable end-to-end model that combines information from both the utterance and the conversational context to detect sarcasm, and demonstrate its effectiveness through empirical evaluations. We also study the behavior of the proposed model to provide explanations for the model’s decisions. Importantly, our model is capable of determining the impact of utterance and conversational context on the model’s decisions. Finally, we provide an ablation study to illustrate the impact of different components of the proposed model.
Tasks	Sarcasm Detection
Published	2018-09-09
URL	http://arxiv.org/abs/1809.03051v1
PDF	http://arxiv.org/pdf/1809.03051v1.pdf
PWC	https://paperswithcode.com/paper/attentional-multi-reading-sarcasm-detection
Repo
Framework

Forecasting Internally Displaced Population Migration Patterns in Syria and Yemen


Title	Forecasting Internally Displaced Population Migration Patterns in Syria and Yemen
Authors	Benjamin Q. Huynh, Sanjay Basu
Abstract	Armed conflict has led to an unprecedented number of internally displaced persons (IDPs) - individuals who are forced out of their homes but remain within their country. IDPs often urgently require shelter, food, and healthcare, yet prediction of when large fluxes of IDPs will cross into an area remains a major challenge for aid delivery organizations. Accurate forecasting of IDP migration would empower humanitarian aid groups to more effectively allocate resources during conflicts. We show that monthly flow of IDPs from province to province in both Syria and Yemen can be accurately forecasted one month in advance, using publicly available data. We model monthly IDP flow using data on food price, fuel price, wage, geospatial, and news data. We find that machine learning approaches can more accurately forecast migration trends than baseline persistence models. Our findings thus potentially enable proactive aid allocation for IDPs in anticipation of forecasted arrivals.
Tasks
Published	2018-06-22
URL	http://arxiv.org/abs/1806.08819v1
PDF	http://arxiv.org/pdf/1806.08819v1.pdf
PWC	https://paperswithcode.com/paper/forecasting-internally-displaced-population
Repo
Framework

Neural Networks in Adversarial Setting and Ill-Conditioned Weight Space


Title	Neural Networks in Adversarial Setting and Ill-Conditioned Weight Space
Authors	Mayank Singh, Abhishek Sinha, Balaji Krishnamurthy
Abstract	Recently, Neural networks have seen a huge surge in its adoption due to their ability to provide high accuracy on various tasks. On the other hand, the existence of adversarial examples have raised suspicions regarding the generalization capabilities of neural networks. In this work, we focus on the weight matrix learnt by the neural networks and hypothesize that ill conditioned weight matrix is one of the contributing factors in neural network’s susceptibility towards adversarial examples. For ensuring that the learnt weight matrix’s condition number remains sufficiently low, we suggest using orthogonal regularizer. We show that this indeed helps in increasing the adversarial accuracy on MNIST and F-MNIST datasets.
Tasks
Published	2018-01-03
URL	http://arxiv.org/abs/1801.00905v1
PDF	http://arxiv.org/pdf/1801.00905v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-in-adversarial-setting-and
Repo
Framework

Multi-scale aggregation of phase information for reducing computational cost of CNN based DOA estimation


Title	Multi-scale aggregation of phase information for reducing computational cost of CNN based DOA estimation
Authors	Soumitro Chakrabarty, Emanuël A. P. Habets
Abstract	In a recent work on direction-of-arrival (DOA) estimation of multiple speakers with convolutional neural networks (CNNs), the phase component of short-time Fourier transform (STFT) coefficients of the microphone signal is given as input and small filters are used to learn the phase relations between neighboring microphones. Due to this chosen filter size, $M-1$ convolution layers are required to achieve the best performance for a microphone array with M microphones. For arrays with large number of microphones, this requirement leads to a high computational cost making the method practically infeasible. In this work, we propose to use systematic dilations of the convolution filters in each of the convolution layers of the previously proposed CNN for expansion of the receptive field of the filters to reduce the computational cost of the method. Different strategies for expansion of the receptive field of the filters for a specific microphone array are explored. With experimental analysis of the different strategies, it is shown that an aggressive expansion strategy results in a considerable reduction in computational cost while a relatively gradual expansion of the receptive field exhibits the best DOA estimation performance along with reduction in the computational cost.
Tasks
Published	2018-11-20
URL	http://arxiv.org/abs/1811.08552v1
PDF	http://arxiv.org/pdf/1811.08552v1.pdf
PWC	https://paperswithcode.com/paper/multi-scale-aggregation-of-phase-information
Repo
Framework

A mixture model for aggregation of multiple pre-trained weak classifiers


Title	A mixture model for aggregation of multiple pre-trained weak classifiers
Authors	Rudrasis Chakraborty, Chun-Hao Yang, Baba C. Vemuri
Abstract	Deep networks have gained immense popularity in Computer Vision and other fields in the past few years due to their remarkable performance on recognition/classification tasks surpassing the state-of-the art. One of the keys to their success lies in the richness of the automatically learned features. In order to get very good accuracy, one popular option is to increase the depth of the network. Training such a deep network is however infeasible or impractical with moderate computational resources and budget. The other alternative to increase the performance is to learn multiple weak classifiers and boost their performance using a boosting algorithm or a variant thereof. But, one of the problems with boosting algorithms is that they require a re-training of the networks based on the misclassified samples. Motivated by these problems, in this work we propose an aggregation technique which combines the output of multiple weak classifiers. We formulate the aggregation problem using a mixture model fitted to the trained classifier outputs. Our model does not require any re-training of the `weak’ networks and is computationally very fast (takes $<30$ seconds to run in our experiments). Thus, using a less expensive training stage and without doing any re-training of networks, we experimentally demonstrate that it is possible to boost the performance by $12%$. Furthermore, we present experiments using hand-crafted features and improved the classification performance using the proposed aggregation technique. One of the major advantages of our framework is that our framework allows one to combine features that are very likely to be of distinct dimensions since they are extracted using different networks/algorithms. Our experimental results demonstrate a significant performance gain from the use of our aggregation technique at a very small computational cost. \|
Tasks
Published	2018-05-31
URL	http://arxiv.org/abs/1806.00003v1
PDF	http://arxiv.org/pdf/1806.00003v1.pdf
PWC	https://paperswithcode.com/paper/a-mixture-model-for-aggregation-of-multiple
Repo
Framework

Analysis of Thompson Sampling for Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms


Title	Analysis of Thompson Sampling for Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms
Authors	Alihan Hüyük, Cem Tekin
Abstract	We analyze the regret of combinatorial Thompson sampling (CTS) for the combinatorial multi-armed bandit with probabilistically triggered arms under the semi-bandit feedback setting. We assume that the learner has access to an exact optimization oracle but does not know the expected base arm outcomes beforehand. When the expected reward function is Lipschitz continuous in the expected base arm outcomes, we derive $O(\sum_{i =1}^m \log T / (p_i \Delta_i))$ regret bound for CTS, where $m$ denotes the number of base arms, $p_i$ denotes the minimum non-zero triggering probability of base arm $i$ and $\Delta_i$ denotes the minimum suboptimality gap of base arm $i$. We also compare CTS with combinatorial upper confidence bound (CUCB) via numerical experiments on a cascading bandit problem.
Tasks
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02707v2
PDF	http://arxiv.org/pdf/1809.02707v2.pdf
PWC	https://paperswithcode.com/paper/analysis-of-thompson-sampling-for
Repo
Framework