October 17, 2019

3032 words 15 mins read

Paper Group ANR 823

Controlling the privacy loss with the input feature maps of the layers in convolutional neural networks. Robust Active Learning for Electrocardiographic Signal Classification. COTA: Improving the Speed and Accuracy of Customer Support through Ranking and Deep Networks. Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates. Advers …

Controlling the privacy loss with the input feature maps of the layers in convolutional neural networks


Title	Controlling the privacy loss with the input feature maps of the layers in convolutional neural networks
Authors	Woohyung Chun, Sung-Min Hong, Junho Huh, Inyup Kang
Abstract	We propose the method to sanitize the privacy of the IFM(Input Feature Map)s that are fed into the layers of CNN(Convolutional Neural Network)s. The method introduces the degree of the sanitization that makes the application using a CNN be able to control the privacy loss represented as the ratio of the probabilistic accuracies for original IFM and sanitized IFM. For the sanitization of an IFM, the sample-and-hold based approximation scheme is devised to satisfy an application-specific degree of the sanitization. The scheme approximates an IFM by replacing all the samples in a window with the non-zero sample closest to the mean of the sampling window. It also removes the dependency on CNN configuration by unfolding multi-dimensional IFM tensors into one-dimensional streams to be approximated.
Tasks
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03444v4
PDF	http://arxiv.org/pdf/1805.03444v4.pdf
PWC	https://paperswithcode.com/paper/controlling-the-privacy-loss-with-the-input
Repo
Framework

Robust Active Learning for Electrocardiographic Signal Classification


Title	Robust Active Learning for Electrocardiographic Signal Classification
Authors	Xu Chen, Saratendu Sethi
Abstract	The classification of electrocardiographic (ECG) signals is a challenging problem for healthcare industry. Traditional supervised learning methods require a large number of labeled data which is usually expensive and difficult to obtain for ECG signals. Active learning is well-suited for ECG signal classification as it aims at selecting the best set of labeled data in order to maximize the classification performance. Motivated by the fact that ECG data are usually heavily unbalanced among different classes and the class labels are noisy as they are manually labeled, this paper proposes a novel solution based on robust active learning for addressing these challenges. The key idea is to first apply the clustering of the data in a low dimensional embedded space and then select the most information instances within local clusters. By selecting the most informative instances relying on local average minimal distances, the algorithm tends to select the data for labelling in a more diversified way. Finally, the robustness of the model is further enhanced by adding a novel noisy label reduction scheme after the selection of the labeled data. Experiments on the ECG signal classification from the MIT-BIH arrhythmia database demonstrate the effectiveness of the proposed algorithm.
Tasks	Active Learning
Published	2018-11-21
URL	http://arxiv.org/abs/1811.08919v1
PDF	http://arxiv.org/pdf/1811.08919v1.pdf
PWC	https://paperswithcode.com/paper/robust-active-learning-for
Repo
Framework

COTA: Improving the Speed and Accuracy of Customer Support through Ranking and Deep Networks


Title	COTA: Improving the Speed and Accuracy of Customer Support through Ranking and Deep Networks
Authors	Piero Molino, Huaixiu Zheng, Yi-Chia Wang
Abstract	For a company looking to provide delightful user experiences, it is of paramount importance to take care of any customer issues. This paper proposes COTA, a system to improve speed and reliability of customer support for end users through automated ticket classification and answers selection for support representatives. Two machine learning and natural language processing techniques are demonstrated: one relying on feature engineering (COTA v1) and the other exploiting raw signals through deep learning architectures (COTA v2). COTA v1 employs a new approach that converts the multi-classification task into a ranking problem, demonstrating significantly better performance in the case of thousands of classes. For COTA v2, we propose an Encoder-Combiner-Decoder, a novel deep learning architecture that allows for heterogeneous input and output feature types and injection of prior knowledge through network architecture choices. This paper compares these models and their variants on the task of ticket classification and answer selection, showing model COTA v2 outperforms COTA v1, and analyzes their inner workings and shortcomings. Finally, an A/B test is conducted in a production setting validating the real-world impact of COTA in reducing issue resolution time by 10 percent without reducing customer satisfaction.
Tasks	Answer Selection, Feature Engineering
Published	2018-07-03
URL	http://arxiv.org/abs/1807.01337v1
PDF	http://arxiv.org/pdf/1807.01337v1.pdf
PWC	https://paperswithcode.com/paper/cota-improving-the-speed-and-accuracy-of
Repo
Framework

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates


Title	Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Authors	Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett
Abstract	In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures—arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithms that are provably robust against such failures, with a focus on achieving optimal statistical performance. A main result of this work is a sharp analysis of two robust distributed gradient descent algorithms based on median and trimmed mean operations, respectively. We prove statistical error rates for three kinds of population loss functions: strongly convex, non-strongly convex, and smooth non-convex. In particular, these algorithms are shown to achieve order-optimal statistical error rates for strongly convex losses. To achieve better communication efficiency, we further propose a median-based distributed algorithm that is provably robust, and uses only one communication round. For strongly convex quadratic loss, we show that this algorithm achieves the same optimal error rate as the robust distributed gradient descent algorithms.
Tasks
Published	2018-03-05
URL	http://arxiv.org/abs/1803.01498v1
PDF	http://arxiv.org/pdf/1803.01498v1.pdf
PWC	https://paperswithcode.com/paper/byzantine-robust-distributed-learning-towards
Repo
Framework

Adversarial Video Compression Guided by Soft Edge Detection


Title	Adversarial Video Compression Guided by Soft Edge Detection
Authors	Sungsoo Kim, Jin Soo Park, Christos G. Bampis, Jaeseong Lee, Mia K. Markey, Alexandros G. Dimakis, Alan C. Bovik
Abstract	We propose a video compression framework using conditional Generative Adversarial Networks (GANs). We rely on two encoders: one that deploys a standard video codec and another which generates low-level maps via a pipeline of down-sampling, a newly devised soft edge detector, and a novel lossless compression scheme. For decoding, we use a standard video decoder as well as a neural network based one, which is trained using a conditional GAN. Recent “deep” approaches to video compression require multiple videos to pre-train generative networks to conduct interpolation. In contrast to this prior work, our scheme trains a generative decoder on pairs of a very limited number of key frames taken from a single video and corresponding low-level maps. The trained decoder produces reconstructed frames relying on a guidance of low-level maps, without any interpolation. Experiments on a diverse set of 131 videos demonstrate that our proposed GAN-based compression engine achieves much higher quality reconstructions at very low bitrates than prevailing standard codecs such as H.264 or HEVC.
Tasks	Edge Detection, Video Compression
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10673v1
PDF	http://arxiv.org/pdf/1811.10673v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-video-compression-guided-by-soft
Repo
Framework


Title	Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation
Authors	Micah J Sheller, G Anthony Reina, Brandon Edwards, Jason Martin, Spyridon Bakas
Abstract	Deep learning models for semantic segmentation of images require large amounts of data. In the medical imaging domain, acquiring sufficient data is a significant challenge. Labeling medical image data requires expert knowledge. Collaboration between institutions could address this challenge, but sharing medical data to a centralized location faces various legal, privacy, technical, and data-ownership challenges, especially among international institutions. In this study, we introduce the first use of federated learning for multi-institutional collaboration, enabling deep learning modeling without sharing patient data. Our quantitative results demonstrate that the performance of federated semantic segmentation models (Dice=0.852) on multimodal brain scans is similar to that of models trained by sharing data (Dice=0.862). We compare federated learning with two alternative collaborative learning methods and find that they fail to match the performance of federated learning.
Tasks	Brain Tumor Segmentation, Semantic Segmentation
Published	2018-10-10
URL	http://arxiv.org/abs/1810.04304v2
PDF	http://arxiv.org/pdf/1810.04304v2.pdf
PWC	https://paperswithcode.com/paper/multi-institutional-deep-learning-modeling
Repo
Framework

Adversarial Attacks on Deep-Learning Based Radio Signal Classification


Title	Adversarial Attacks on Deep-Learning Based Radio Signal Classification
Authors	Meysam Sadeghi, Erik G. Larsson
Abstract	Deep learning (DL), despite its enormous success in many computer vision and language processing applications, is exceedingly vulnerable to adversarial attacks. We consider the use of DL for radio signal (modulation) classification tasks, and present practical methods for the crafting of white-box and universal black-box adversarial attacks in that application. We show that these attacks can considerably reduce the classification performance, with extremely small perturbations of the input. In particular, these attacks are significantly more powerful than classical jamming attacks, which raises significant security and robustness concerns in the use of DL-based algorithms for the wireless physical layer.
Tasks
Published	2018-08-23
URL	http://arxiv.org/abs/1808.07713v1
PDF	http://arxiv.org/pdf/1808.07713v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-attacks-on-deep-learning-based
Repo
Framework

Computing the Spatial Probability of Inclusion inside Partial Contours for Computer Vision Applications


Title	Computing the Spatial Probability of Inclusion inside Partial Contours for Computer Vision Applications
Authors	Dominique Beaini, Sofiane Achiche, Fabrice Nonez, Maxime Raison
Abstract	In Computer Vision, edge detection is one of the favored approaches for feature and object detection in images since it provides information about their objects boundaries. Other region-based approaches use probabilistic analysis such as clustering and Markov random fields, but those methods cannot be used to analyze edges and their interaction. In fact, only image segmentation can produce regions based on edges, but it requires thresholding by simply separating the regions into binary in-out information. Hence, there is currently a gap between edge-based and region-based algorithms, since edges cannot be used to study the properties of a region and vice versa. The objective of this paper is to present a novel spatial probability analysis that allows determining the probability of inclusion inside a set of partial contours (strokes). To answer this objective, we developed a new approach that uses electromagnetic convolutions and repulsion optimization to compute the required probabilities. Hence, it becomes possible to generate a continuous space of probability based only on the edge information, thus bridging the gap between the edge-based methods and the region-based methods. The developed method is consistent with the fundamental properties of inclusion probabilities and its results are validated by comparing an image with the probability-based estimation given by our algorithm. The method can also be generalized to take into consideration the intensity of the edges or to be used for 3D shapes. This is the first documented method that allows computing a space of probability based on interacting edges, which opens the path to broader applications such as image segmentation and contour completion.
Tasks	Edge Detection, Object Detection, Semantic Segmentation
Published	2018-06-04
URL	https://arxiv.org/abs/1806.01339v2
PDF	https://arxiv.org/pdf/1806.01339v2.pdf
PWC	https://paperswithcode.com/paper/computing-the-spatial-probability-of
Repo
Framework

Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation


Title	Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation
Authors	Maximilian Jaritz, Raoul de Charette, Emilie Wirbel, Xavier Perrotton, Fawzi Nashashibi
Abstract	Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth completion and semantic segmentation changing only the last layer. Our proposal efficiently learns sparse features without the need of an additional validity mask. We show how to ensure network robustness to varying input sparsities. Our method even works with densities as low as 0.8% (8 layer lidar), and outperforms all published state-of-the-art on the Kitti depth completion benchmark.
Tasks	Depth Completion, Semantic Segmentation
Published	2018-08-02
URL	http://arxiv.org/abs/1808.00769v2
PDF	http://arxiv.org/pdf/1808.00769v2.pdf
PWC	https://paperswithcode.com/paper/sparse-and-dense-data-with-cnns-depth
Repo
Framework

Part-based Visual Tracking via Structural Support Correlation Filter


Title	Part-based Visual Tracking via Structural Support Correlation Filter
Authors	Zhangjian Ji, Kai Feng, Yuhua Qian
Abstract	Recently, part-based and support vector machines (SVM) based trackers have shown favorable performance. Nonetheless, the time-consuming online training and updating process limit their real-time applications. In order to better deal with the partial occlusion issue and improve their efficiency, we propose a novel part-based structural support correlation filter tracking method, which absorbs the strong discriminative ability from SVM and the excellent property of part-based tracking methods which is less sensitive to partial occlusion. Then, our proposed model can learn the support correlation filter of each part jointly by a star structure model, which preserves the spatial layout structure among parts and tolerates outliers of parts. In addition, to mitigate the issue of drift away from object further, we introduce inter-frame consistencies of local parts into our model. Finally, in our model, we accurately estimate the scale changes of object by the relative distance change among reliable parts. The extensive empirical evaluations on three benchmark datasets: OTB2015, TempleColor128 and VOT2015 demonstrate that the proposed method performs superiorly against several state-of-the-art trackers in terms of tracking accuracy, speed and robustness.
Tasks	Visual Tracking
Published	2018-05-25
URL	http://arxiv.org/abs/1805.09971v1
PDF	http://arxiv.org/pdf/1805.09971v1.pdf
PWC	https://paperswithcode.com/paper/part-based-visual-tracking-via-structural
Repo
Framework

Limited Evaluation Cooperative Co-evolutionary Differential Evolution for Large-scale Neuroevolution


Title	Limited Evaluation Cooperative Co-evolutionary Differential Evolution for Large-scale Neuroevolution
Authors	Anil Yaman, Decebal Constantin Mocanu, Giovanni Iacca, George Fletcher, Mykola Pechenizkiy
Abstract	Many real-world control and classification tasks involve a large number of features. When artificial neural networks (ANNs) are used for modeling these tasks, the network architectures tend to be large. Neuroevolution is an effective approach for optimizing ANNs; however, there are two bottlenecks that make their application challenging in case of high-dimensional networks using direct encoding. First, classic evolutionary algorithms tend not to scale well for searching large parameter spaces; second, the network evaluation over a large number of training instances is in general time-consuming. In this work, we propose an approach called the Limited Evaluation Cooperative Co-evolutionary Differential Evolution algorithm (LECCDE) to optimize high-dimensional ANNs. The proposed method aims to optimize the pre-synaptic weights of each post-synaptic neuron in different subpopulations using a Cooperative Co-evolutionary Differential Evolution algorithm, and employs a limited evaluation scheme where fitness evaluation is performed on a relatively small number of training instances based on fitness inheritance. We test LECCDE on three datasets with various sizes, and our results show that cooperative co-evolution significantly improves the test error comparing to standard Differential Evolution, while the limited evaluation scheme facilitates a significant reduction in computing time.
Tasks
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07234v2
PDF	http://arxiv.org/pdf/1804.07234v2.pdf
PWC	https://paperswithcode.com/paper/limited-evaluation-cooperative-co
Repo
Framework

Wafer Quality Inspection using Memristive LSTM, ANN, DNN and HTM


Title	Wafer Quality Inspection using Memristive LSTM, ANN, DNN and HTM
Authors	Kazybek Adam, Kamilya Smagulova, Olga Krestinskaya, Alex Pappachen James
Abstract	The automated wafer inspection and quality control is a complex and time-consuming task, which can speed up using neuromorphic memristive architectures, as a separate inspection device or integrating directly into sensors. This paper presents the performance analysis and comparison of different neuromorphic architectures for patterned wafer quality inspection and classification. The application of non-volatile memristive devices in these architectures ensures low power consumption, small on-chip area scalability. We demonstrate that Long-Short Term Memory (LSTM) outperforms other architectures for the same number of training iterations, and has relatively low on-chip area and power consumption.
Tasks
Published	2018-09-27
URL	http://arxiv.org/abs/1809.10438v1
PDF	http://arxiv.org/pdf/1809.10438v1.pdf
PWC	https://paperswithcode.com/paper/wafer-quality-inspection-using-memristive
Repo
Framework

Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection


Title	Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection
Authors	Weicheng Kuo, Christian Häne, Esther Yuh, Pratik Mukherjee, Jitendra Malik
Abstract	Deep learning for clinical applications is subject to stringent performance requirements, which raises a need for large labeled datasets. However, the enormous cost of labeling medical data makes this challenging. In this paper, we build a cost-sensitive active learning system for the problem of intracranial hemorrhage detection and segmentation on head computed tomography (CT). We show that our ensemble method compares favorably with the state-of-the-art, while running faster and using less memory. Moreover, our experiments are done using a substantially larger dataset than earlier papers on this topic. Since the labeling time could vary tremendously across examples, we model the labeling time and optimize the return on investment. We validate this idea by core-set selection on our large labeled dataset and by growing it with data from the wild.
Tasks	Active Learning, Computed Tomography (CT)
Published	2018-09-08
URL	http://arxiv.org/abs/1809.02882v1
PDF	http://arxiv.org/pdf/1809.02882v1.pdf
PWC	https://paperswithcode.com/paper/cost-sensitive-active-learning-for
Repo
Framework

Generating Levels That Teach Mechanics


Title	Generating Levels That Teach Mechanics
Authors	Michael Cerny Green, Ahmed Khalifa, Gabriella A. B. Barros, Andy Nealen, Julian Togelius
Abstract	The automatic generation of game tutorials is a challenging AI problem. While it is possible to generate annotations and instructions that explain to the player how the game is played, this paper focuses on generating a gameplay experience that introduces the player to a game mechanic. It evolves small levels for the Mario AI Framework that can only be beaten by an agent that knows how to perform specific actions in the game. It uses variations of a perfect A* agent that are limited in various ways, such as not being able to jump high or see enemies, to test how failing to do certain actions can stop the player from beating the level.
Tasks
Published	2018-07-18
URL	http://arxiv.org/abs/1807.06734v4
PDF	http://arxiv.org/pdf/1807.06734v4.pdf
PWC	https://paperswithcode.com/paper/generating-levels-that-teach-mechanics
Repo
Framework

Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profiles


Title	Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profiles
Authors	Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan Read, Jacob Zwart, Michael Steinbach, Vipin Kumar
Abstract	This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physical models, while generating outputs consistent with physical laws, and achieving good generalizability. Standard RNNs, even when producing superior prediction accuracy, often produce physically inconsistent results and lack generalizability. We further enhance this approach by using a pre-training method that leverages the simulated data from a physics-based model to address the scarcity of observed data. The PGRNN has the flexibility to incorporate additional physical constraints and we incorporate a density-depth relationship. Both enhancements further improve PGRNN performance. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where mechanistic (also known as process-based) models are used, e.g., power engineering, climate science, materials science, computational chemistry, and biomedicine.
Tasks
Published	2018-10-31
URL	http://arxiv.org/abs/1810.13075v2
PDF	http://arxiv.org/pdf/1810.13075v2.pdf
PWC	https://paperswithcode.com/paper/physics-guided-rnns-for-modeling-dynamical
Repo
Framework