January 29, 2020

2775 words 14 mins read

Paper Group ANR 767

Lightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote Inference. Beyond Top-Grasps Through Scene Completion. Trajectory-Based Recognition of Dynamic Persian Sign Language Using Hidden Markov Model. Neural Decoder for Topological Codes using Pseudo-Inverse of Parity Check Matrix. A Baseline Neural Machine Translation System for Indian …

Lightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote Inference


Title	Lightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote Inference
Authors	Dixing Xu, Mengyao Zheng, Linshan Jiang, Chaojie Gu, Rui Tan, Peng Cheng
Abstract	Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the need to protect the confidentiality of the inference neural networks. However, such a remote inference scheme incurs concerns regarding the privacy of the inference data transmitted by the edge devices to the curious backend. This paper presents a lightweight and unobtrusive approach to obfuscate the inference data at the edge devices. It is lightweight in that the edge device only needs to execute a small-scale neural network; it is unobtrusive in that the edge device does not need to indicate whether obfuscation is applied. Extensive evaluation by three case studies of free spoken digit recognition, handwritten digit recognition, and American sign language recognition shows that our approach effectively protects the confidentiality of the raw forms of the inference data while effectively preserving the backend’s inference accuracy.
Tasks	Handwritten Digit Recognition, Sign Language Recognition
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09859v3
PDF	https://arxiv.org/pdf/1912.09859v3.pdf
PWC	https://paperswithcode.com/paper/lightweight-and-unobtrusive-privacy
Repo
Framework

Beyond Top-Grasps Through Scene Completion


Title	Beyond Top-Grasps Through Scene Completion
Authors	Jens Lundell, Francesco Verdoja, Ville Kyrki
Abstract	Current end-to-end grasp planning methods propose grasps in the order of seconds that attain high grasp success rates on a diverse set of objects, but often by constraining the workspace to top-grasps. In this work, we present a method that allows end-to-end top-grasp planning methods to generate full six-degree-of-freedom grasps using a single RGB-D view as input. This is achieved by estimating the complete shape of the object to be grasped, then simulating different viewpoints of the object, passing the simulated viewpoints to an end-to-end grasp generation method, and finally executing the overall best grasp. The method was experimentally validated on a Franka Emika Panda by comparing 429 grasps generated by the state-of-the-art Fully Convolutional Grasp Quality CNN, both on simulated and real camera images. The results show statistically significant improvements in terms of grasp success rate when using simulated images over real camera images, especially when the real camera viewpoint is angled. Code and video are available at https://irobotics.aalto.fi/beyond-top-grasps-through-scene-completion/.
Tasks
Published	2019-09-15
URL	https://arxiv.org/abs/1909.12908v2
PDF	https://arxiv.org/pdf/1909.12908v2.pdf
PWC	https://paperswithcode.com/paper/beyond-top-grasps-through-scene-completion
Repo
Framework

Trajectory-Based Recognition of Dynamic Persian Sign Language Using Hidden Markov Model


Title	Trajectory-Based Recognition of Dynamic Persian Sign Language Using Hidden Markov Model
Authors	Saeideh Ghanbari Azar, Hadi Seyedarabi
Abstract	Sign Language Recognition (SLR) is an important step in facilitating the communication among deaf people and the rest of society. Existing Persian sign language recognition systems are mainly restricted to static signs which are not very useful in everyday communications. In this study, a dynamic Persian sign language recognition system is presented. A collection of 1200 videos were captured from 12 individuals performing 20 dynamic signs with a simple white glove. The trajectory of the hands, along with hand shape information were extracted from each video using a simple region-growing technique. These time-varying trajectories were then modeled using Hidden Markov Model (HMM) with Gaussian probability density functions as observations. The performance of the system was evaluated in different experimental strategies. Signer-independent and signer-dependent experiments were performed on the proposed system and the average accuracy of 97.48% was obtained. The experimental results demonstrated that the performance of the system is independent of the subject and it can also perform excellently even with a limited number of training data.
Tasks	Sign Language Recognition
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01944v1
PDF	https://arxiv.org/pdf/1912.01944v1.pdf
PWC	https://paperswithcode.com/paper/trajectory-based-recognition-of-dynamic
Repo
Framework

Neural Decoder for Topological Codes using Pseudo-Inverse of Parity Check Matrix


Title	Neural Decoder for Topological Codes using Pseudo-Inverse of Parity Check Matrix
Authors	Chaitanya Chinni, Abhishek Kulkarni, Dheeraj M. Pai, Kaushik Mitra, Pradeep Kiran Sarvepalli
Abstract	Recent developments in the field of deep learning have motivated many researchers to apply these methods to problems in quantum information. Torlai and Melko first proposed a decoder for surface codes based on neural networks. Since then, many other researchers have applied neural networks to study a variety of problems in the context of decoding. An important development in this regard was due to Varsamopoulos et al. who proposed a two-step decoder using neural networks. Subsequent work of Maskara et al. used the same concept for decoding for various noise models. We propose a similar two-step neural decoder using inverse parity-check matrix for topological color codes. We show that it outperforms the state-of-the-art performance of non-neural decoders for independent Pauli errors noise model on a 2D hexagonal color code. Our final decoder is independent of the noise model and achieves a threshold of $10 %$. Our result is comparable to the recent work on neural decoder for quantum error correction by Maskara et al.. It appears that our decoder has significant advantages with respect to training cost and complexity of the network for higher lengths when compared to that of Maskara et al.. Our proposed method can also be extended to arbitrary dimension and other stabilizer codes.
Tasks
Published	2019-01-21
URL	http://arxiv.org/abs/1901.07535v2
PDF	http://arxiv.org/pdf/1901.07535v2.pdf
PWC	https://paperswithcode.com/paper/neural-decoder-for-topological-codes-using
Repo
Framework

A Baseline Neural Machine Translation System for Indian Languages


Title	A Baseline Neural Machine Translation System for Indian Languages
Authors	Jerin Philip, Vinay P. Namboodiri, C. V. Jawahar
Abstract	We present a simple, yet effective, Neural Machine Translation system for Indian languages. We demonstrate the feasibility for multiple language pairs, and establish a strong baseline for further research.
Tasks	Machine Translation
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12437v1
PDF	https://arxiv.org/pdf/1907.12437v1.pdf
PWC	https://paperswithcode.com/paper/a-baseline-neural-machine-translation-system
Repo
Framework

A Light weight and Hybrid Deep Learning Model based Online Signature Verification


Title	A Light weight and Hybrid Deep Learning Model based Online Signature Verification
Authors	Chandra Sekhar V., Anoushka Doctor, Prerana Mukherjee, Viswanath Pulabaigiri
Abstract	The augmented usage of deep learning-based models for various AI related problems are as a result of modern architectures of deeper length and the availability of voluminous interpreted datasets. The models based on these architectures require huge training and storage cost, which makes them inefficient to use in critical applications like online signature verification (OSV) and to deploy in resource constraint devices. As a solution, in this work, our contribution is two-fold. 1) An efficient dimensionality reduction technique, to reduce the number of features to be considered and 2) a state-of-the-art model CNN-LSTM based hybrid architecture for online signature verification. Thorough experiments on the publicly available datasets MCYT, SUSIG, SVC confirms that the proposed model achieves better accuracy even with as low as one training sample. The proposed models yield state-of-the-art performance in various categories of all the three datasets.
Tasks	Dimensionality Reduction
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04061v1
PDF	https://arxiv.org/pdf/1907.04061v1.pdf
PWC	https://paperswithcode.com/paper/a-light-weight-and-hybrid-deep-learning-model
Repo
Framework

E.T.-RNN: Applying Deep Learning to Credit Loan Applications


Title	E.T.-RNN: Applying Deep Learning to Credit Loan Applications
Authors	Dmitrii Babaev, Maxim Savchenko, Alexander Tuzhilin, Dmitrii Umerenkov
Abstract	In this paper we present a novel approach to credit scoring of retail customers in the banking industry based on deep learning methods. We used RNNs on fine grained transnational data to compute credit scores for the loan applicants. We demonstrate that our approach significantly outperforms the baselines based on the customer data of a large European bank. We also conducted a pilot study on loan applicants of the bank, and the study produced significant financial gains for the organization. In addition, our method has several other advantages described in the paper that are very significant for the bank.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02496v1
PDF	https://arxiv.org/pdf/1911.02496v1.pdf
PWC	https://paperswithcode.com/paper/et-rnn-applying-deep-learning-to-credit-loan
Repo
Framework

Multiclass Language Identification using Deep Learning on Spectral Images of Audio Signals


Title	Multiclass Language Identification using Deep Learning on Spectral Images of Audio Signals
Authors	Shauna Revay, Matthew Teschke
Abstract	The first step in any voice recognition software is to determine what language a speaker is using, and ideally this process would be automated. The technique described in this paper, language identification for audio spectrograms (LIFAS), uses spectrograms generated from audio signals as inputs to a convolutional neural network (CNN) to be used for language identification. LIFAS requires minimal pre-processing on the audio signals as the spectrograms are generated during each batch as they are input to the network during training. LIFAS utilizes deep learning tools that are shown to be successful on image processing tasks and applies it to audio signal classification. LIFAS performs binary language classification with an accuracy of 97%, and multi-class classification with six languages at an accuracy of 89% on 3.75 second audio clips.
Tasks	Language Identification
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04348v1
PDF	https://arxiv.org/pdf/1905.04348v1.pdf
PWC	https://paperswithcode.com/paper/multiclass-language-identification-using-deep
Repo
Framework

ProtoGAN: Towards Few Shot Learning for Action Recognition


Title	ProtoGAN: Towards Few Shot Learning for Action Recognition
Authors	Sai Kumar Dwivedi, Vikram Gupta, Rahul Mitra, Shuaib Ahmed, Arjun Jain
Abstract	Few-shot learning (FSL) for action recognition is a challenging task of recognizing novel action categories which are represented by few instances in the training data. In a more generalized FSL setting (G-FSL), both seen as well as novel action categories need to be recognized. Conventional classifiers suffer due to inadequate data in FSL setting and inherent bias towards seen action categories in G-FSL setting. In this paper, we address this problem by proposing a novel ProtoGAN framework which synthesizes additional examples for novel categories by conditioning a conditional generative adversarial network with class prototype vectors. These class prototype vectors are learnt using a Class Prototype Transfer Network (CPTN) from examples of seen categories. Our synthesized examples for a novel class are semantically similar to real examples belonging to that class and is used to train a model exhibiting better generalization towards novel classes. We support our claim by performing extensive experiments on three datasets: UCF101, HMDB51 and Olympic-Sports. To the best of our knowledge, we are the first to report the results for G-FSL and provide a strong benchmark for future research. We also outperform the state-of-the-art method in FSL for all the aforementioned datasets.
Tasks	Few-Shot Learning
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07945v1
PDF	https://arxiv.org/pdf/1909.07945v1.pdf
PWC	https://paperswithcode.com/paper/protogan-towards-few-shot-learning-for-action
Repo
Framework

Unscented Gaussian Process Latent Variable Model: learning from uncertain inputs with intractable kernels


Title	Unscented Gaussian Process Latent Variable Model: learning from uncertain inputs with intractable kernels
Authors	Daniel Augusto R. M. A. de Souza, César Lincoln C. Mattos, João Paulo P. Gomes
Abstract	The Gaussian Process (GP) framework flexibility has enabled its use in several data modeling scenarios. The setting where we have unavailable or uncertain inputs that generate possibly noisy observations is usually tackled by the well known Gaussian Process Latent Variable Model (GPLVM). However, the standard variational approach to perform inference with the GPLVM presents some expressions that are tractable for only a few kernel functions, which may hinder its general application. While other quadrature or sampling approaches could be used in that case, they usually are very slow and/or non-deterministic. In the present paper, we propose the use of the unscented transformation to enable the use of any kernel function within the Bayesian GPLVM. Our approach maintains the fully deterministic feature of tractable kernels and presents a simple implementation with only moderate computational cost. Experiments on dimensionality reduction and multistep-ahead prediction with uncertainty propagation indicate the feasibility of our proposal.
Tasks	Dimensionality Reduction
Published	2019-07-03
URL	https://arxiv.org/abs/1907.01867v1
PDF	https://arxiv.org/pdf/1907.01867v1.pdf
PWC	https://paperswithcode.com/paper/unscented-gaussian-process-latent-variable
Repo
Framework

Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods


Title	Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
Authors	Aditya Mogadala, Marimuthu Kalimuthu, Dietrich Klakow
Abstract	Integration of vision and language tasks has seen a significant growth in the recent times due to surge of interest from multi-disciplinary communities such as deep learning, computer vision, and natural language processing. In this survey, we focus on ten different vision and language integration tasks in terms of their problem formulation, methods, existing datasets, evaluation measures, and comparison of results achieved with the corresponding state-of-the-art methods. This goes beyond earlier surveys which are either task-specific or concentrate only on one type of visual content i.e., image or video. We then conclude the survey by discussing some possible future directions for integration of vision and language research.
Tasks
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09358v1
PDF	https://arxiv.org/pdf/1907.09358v1.pdf
PWC	https://paperswithcode.com/paper/trends-in-integration-of-vision-and-language
Repo
Framework

Generalized Principal Component Analysis


Title	Generalized Principal Component Analysis
Authors	F. William Townes
Abstract	Generalized principal component analysis (GLM-PCA) facilitates dimension reduction of non-normally distributed data. We provide a detailed derivation of GLM-PCA with a focus on optimization. We also demonstrate how to incorporate covariates, and suggest post-processing transformations to improve interpretability of latent factors.
Tasks	Dimensionality Reduction
Published	2019-07-03
URL	https://arxiv.org/abs/1907.02647v1
PDF	https://arxiv.org/pdf/1907.02647v1.pdf
PWC	https://paperswithcode.com/paper/generalized-principal-component-analysis
Repo
Framework

Anomaly Detection with HMM Gauge Likelihood Analysis


Title	Anomaly Detection with HMM Gauge Likelihood Analysis
Authors	Boris Lorbeer, Tanja Deutsch, Peter Ruppel, Axel Küpper
Abstract	This paper describes a new method, HMM gauge likelihood analysis, or GLA, of detecting anomalies in discrete time series using Hidden Markov Models and clustering. At the center of the method lies the comparison of subsequences. To achieve this, they first get assigned to their Hidden Markov Models using the Baum-Welch algorithm. Next, those models are described by an approximating representation of the probability distributions they define. Finally, this representation is then analyzed with the help of some clustering technique or other outlier detection tool and anomalies are detected. Clearly, HMMs could be substituted by some other appropriate model, e.g. some other dynamic Bayesian network. Our learning algorithm is unsupervised, so it does not require the labeling of large amounts of data. The usability of this method is demonstrated by applying it to synthetic and real-world syslog data.
Tasks	Anomaly Detection, Outlier Detection, Time Series
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06134v1
PDF	https://arxiv.org/pdf/1906.06134v1.pdf
PWC	https://paperswithcode.com/paper/anomaly-detection-with-hmm-gauge-likelihood
Repo
Framework

Nonconvex Approach for Sparse and Low-Rank Constrained Models with Dual Momentum


Title	Nonconvex Approach for Sparse and Low-Rank Constrained Models with Dual Momentum
Authors	Cho-Ying Wu, Jian-Jiun Ding
Abstract	In this manuscript, we research on the behaviors of surrogates for the rank function on different image processing problems and their optimization algorithms. We first propose a novel nonconvex rank surrogate on the general rank minimization problem and apply this to the corrupted image completion problem. Then, we propose that nonconvex rank surrogates can be introduced into two well-known sparse and low-rank models: Robust Principal Component Analysis (RPCA) and Low-Rank Representation (LRR). For optimization, we use alternating direction method of multipliers (ADMM) and propose a trick, which is called the dual momentum. We add the difference of the dual variable between the current and the last iteration with a weight. This trick can avoid the local minimum problem and make the algorithm converge to a solution with smaller recovery error in the nonconvex optimization problem. Also, it can boost the convergence when the variable updates too slowly. We also give a severe proof and verify that the proposed algorithms are convergent. Then, several experiments are conducted, including image completion, denoising, and spectral clustering with outlier detection. These experiments show that the proposed methods are effective in image and signal processing applications, and have the best performance compared with state-of-the-art methods.
Tasks	Denoising, Outlier Detection
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02433v1
PDF	https://arxiv.org/pdf/1906.02433v1.pdf
PWC	https://paperswithcode.com/paper/nonconvex-approach-for-sparse-and-low-rank
Repo
Framework

MaxGap Bandit: Adaptive Algorithms for Approximate Ranking


Title	MaxGap Bandit: Adaptive Algorithms for Approximate Ranking
Authors	Sumeet Katariya, Ardhendu Tripathy, Robert Nowak
Abstract	This paper studies the problem of adaptively sampling from K distributions (arms) in order to identify the largest gap between any two adjacent means. We call this the MaxGap-bandit problem. This problem arises naturally in approximate ranking, noisy sorting, outlier detection, and top-arm identification in bandits. The key novelty of the MaxGap-bandit problem is that it aims to adaptively determine the natural partitioning of the distributions into a subset with larger means and a subset with smaller means, where the split is determined by the largest gap rather than a pre-specified rank or threshold. Estimating an arm’s gap requires sampling its neighboring arms in addition to itself, and this dependence results in a novel hardness parameter that characterizes the sample complexity of the problem. We propose elimination and UCB-style algorithms and show that they are minimax optimal. Our experiments show that the UCB-style algorithms require 6-8x fewer samples than non-adaptive sampling to achieve the same error.
Tasks	Outlier Detection
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00547v1
PDF	https://arxiv.org/pdf/1906.00547v1.pdf
PWC	https://paperswithcode.com/paper/190600547
Repo
Framework