October 21, 2019

3164 words 15 mins read

Paper Group AWR 76

Deep Quality-Value (DQV) Learning. AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy. Regularized Wasserstein Means for Aligning Distributional Data. Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators. Recurrent Neural Networks for Fuzz Testing Web Browsers. Parsimonious Bay …

Deep Quality-Value (DQV) Learning


Title	Deep Quality-Value (DQV) Learning
Authors	Matthia Sabatelli, Gilles Louppe, Pierre Geurts, Marco A. Wiering
Abstract	We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that learns to estimate state-action values. We first test DQV’s update rules with Multilayer Perceptrons as function approximators on two classic RL problems, and then extend DQV with the use of Deep Convolutional Neural Networks, `Experience Replay' and` Target Neural Networks’ for tackling four games of the Atari Arcade Learning environment. Our results show that DQV learns significantly faster and better than Deep Q-Learning and Double Deep Q-Learning, suggesting that our algorithm can potentially be a better performing synchronous temporal difference algorithm than what is currently present in DRL.
Tasks	Atari Games, Q-Learning
Published	2018-09-30
URL	http://arxiv.org/abs/1810.00368v2
PDF	http://arxiv.org/pdf/1810.00368v2.pdf
PWC	https://paperswithcode.com/paper/deep-quality-value-dqv-learning
Repo	https://github.com/paintception/Deep-Quality-Value-DQV-Learning-
Framework	tf

AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy


Title	AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume Segmentation of Head and Neck Anatomy
Authors	Wentao Zhu, Yufang Huang, Liang Zeng, Xuming Chen, Yong Liu, Zhen Qian, Nan Du, Wei Fan, Xiaohui Xie
Abstract	Methods: Our deep learning model, called AnatomyNet, segments OARs from head and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT images as input and generating masks of all OARs of interest in one shot. AnatomyNet is built upon the popular 3D U-net architecture, but extends it in three important ways: 1) a new encoding scheme to allow auto-segmentation on whole-volume CT images instead of local patches or subsets of slices, 2) incorporating 3D squeeze-and-excitation residual blocks in encoding layers for better feature representation, and 3) a new loss function combining Dice scores and focal loss to facilitate the training of the neural model. These features are designed to address two main challenges in deep-learning-based HaN segmentation: a) segmenting small anatomies (i.e., optic chiasm and optic nerves) occupying only a few slices, and b) training with inconsistent data annotations with missing ground truth for some anatomical structures. Results: We collected 261 HaN CT images to train AnatomyNet, and used MICCAI Head and Neck Auto Segmentation Challenge 2015 as a benchmark dataset to evaluate the performance of AnatomyNet. The objective is to segment nine anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right, parotid gland left, parotid gland right, submandibular gland left, and submandibular gland right. Compared to previous state-of-the-art results from the MICCAI 2015 competition, AnatomyNet increases Dice similarity coefficient by 3.3% on average. AnatomyNet takes about 0.12 seconds to fully segment a head and neck CT image of dimension 178 x 302 x 225, significantly faster than previous methods. In addition, the model is able to process whole-volume CT images and delineate all OARs in one pass, requiring little pre- or post-processing. https://github.com/wentaozhu/AnatomyNet-for-anatomical-segmentation.git.
Tasks
Published	2018-08-15
URL	http://arxiv.org/abs/1808.05238v2
PDF	http://arxiv.org/pdf/1808.05238v2.pdf
PWC	https://paperswithcode.com/paper/anatomynet-deep-learning-for-fast-and-fully
Repo	https://github.com/ginn24/ICE3050-41
Framework	tf

Regularized Wasserstein Means for Aligning Distributional Data


Title	Regularized Wasserstein Means for Aligning Distributional Data
Authors	Liang Mi, Wen Zhang, Yalin Wang
Abstract	We propose to align distributional data from the perspective of Wasserstein means. We raise the problem of regularizing Wasserstein means and propose several terms tailored to tackle different problems. Our formulation is based on the variational transportation to distribute a sparse discrete measure into the target domain. The resulting sparse representation well captures the desired property of the domain while reducing the mapping cost. We demonstrate the scalability and robustness of our method with examples in domain adaptation, point set registration, and skeleton layout.
Tasks	Domain Adaptation
Published	2018-12-02
URL	https://arxiv.org/abs/1812.00338v2
PDF	https://arxiv.org/pdf/1812.00338v2.pdf
PWC	https://paperswithcode.com/paper/regularized-wasserstein-means-based-on
Repo	https://github.com/icemiliang/pyvot
Framework	pytorch

Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators


Title	Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators
Authors	Isao Ishikawa, Keisuke Fujii, Masahiro Ikeda, Yuka Hashimoto, Yoshinobu Kawahara
Abstract	The development of a metric for structural data is a long-term problem in pattern recognition and machine learning. In this paper, we develop a general metric for comparing nonlinear dynamical systems that is defined with Perron-Frobenius operators in reproducing kernel Hilbert spaces. Our metric includes the existing fundamental metrics for dynamical systems, which are basically defined with principal angles between some appropriately-chosen subspaces, as its special cases. We also describe the estimation of our metric from finite data. We empirically illustrate our metric with an example of rotation dynamics in a unit disk in a complex plane, and evaluate the performance with real-world time-series data.
Tasks	Time Series
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12324v2
PDF	http://arxiv.org/pdf/1805.12324v2.pdf
PWC	https://paperswithcode.com/paper/metric-on-nonlinear-dynamical-systems-with
Repo	https://github.com/keisuke198619/metricNLDS
Framework	none

Recurrent Neural Networks for Fuzz Testing Web Browsers


Title	Recurrent Neural Networks for Fuzz Testing Web Browsers
Authors	Martin Sablotny, Bjørn Sand Jensen, Chris W. Johnson
Abstract	Generation-based fuzzing is a software testing approach which is able to discover different types of bugs and vulnerabilities in software. It is, however, known to be very time consuming to design and fine tune classical fuzzers to achieve acceptable coverage, even for small-scale software systems. To address this issue, we investigate a machine learning-based approach to fuzz testing in which we outline a family of test-case generators based on Recurrent Neural Networks (RNNs) and train those on readily available datasets with a minimum of human fine tuning. The proposed generators do, in contrast to previous work, not rely on heuristic sampling strategies but principled sampling from the predictive distributions. We provide a detailed analysis to demonstrate the characteristics and efficacy of the proposed generators in a challenging web browser testing scenario. The empirical results show that the RNN-based generators are able to provide better coverage than a mutation based method and are able to discover paths not discovered by a classical fuzzer. Our results supplement findings in other domains suggesting that generation based fuzzing with RNNs is a viable route to better software quality conditioned on the use of a suitable model selection/analysis procedure.
Tasks	Model Selection
Published	2018-12-12
URL	http://arxiv.org/abs/1812.04852v1
PDF	http://arxiv.org/pdf/1812.04852v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-neural-networks-for-fuzz-testing
Repo	https://github.com/susperius/icisc_rnnfuzz
Framework	tf

Parsimonious Bayesian deep networks


Title	Parsimonious Bayesian deep networks
Authors	Mingyuan Zhou
Abstract	Combining Bayesian nonparametrics and a forward model selection strategy, we construct parsimonious Bayesian deep networks (PBDNs) that infer capacity-regularized network architectures from the data and require neither cross-validation nor fine-tuning when training the model. One of the two essential components of a PBDN is the development of a special infinite-wide single-hidden-layer neural network, whose number of active hidden units can be inferred from the data. The other one is the construction of a greedy layer-wise learning algorithm that uses a forward model selection criterion to determine when to stop adding another hidden layer. We develop both Gibbs sampling and stochastic gradient descent based maximum a posteriori inference for PBDNs, providing state-of-the-art classification accuracy and interpretable data subtypes near the decision boundaries, while maintaining low computational complexity for out-of-sample prediction.
Tasks	Model Selection
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08719v3
PDF	http://arxiv.org/pdf/1805.08719v3.pdf
PWC	https://paperswithcode.com/paper/parsimonious-bayesian-deep-networks
Repo	https://github.com/ethanhezhao/WEDTM
Framework	none

Latent Fingerprint Recognition: Role of Texture Template


Title	Latent Fingerprint Recognition: Role of Texture Template
Authors	Kai Cao, Anil K. Jain
Abstract	We propose a texture template approach, consisting of a set of virtual minutiae, to improve the overall latent fingerprint recognition accuracy. To compensate for the lack of sufficient number of minutiae in poor quality latent prints, we generate a set of virtual minutiae. However, due to a large number of these regularly placed virtual minutiae, texture based template matching has a large computational requirement compared to matching true minutiae templates. To improve both the accuracy and efficiency of the texture template matching, we investigate: i) both original and enhanced fingerprint patches for training convolutional neural networks (ConvNets) to improve the distinctiveness of descriptors associated with each virtual minutiae, ii) smaller patches around virtual minutiae and a fast ConvNet architecture to speed up descriptor extraction, iii) reduce the descriptor length, iv) a modified hierarchical graph matching strategy to improve the matching speed, and v) extraction of multiple texture templates to boost the performance. Experiments on NIST SD27 latent database show that the above strategies can improve the matching speed from 11 ms (24 threads) per comparison (between a latent and a reference print) to only 7.7 ms (single thread) per comparison while improving the rank-1 accuracy by 8.9% against 10K gallery.
Tasks	Graph Matching
Published	2018-04-27
URL	http://arxiv.org/abs/1804.10337v1
PDF	http://arxiv.org/pdf/1804.10337v1.pdf
PWC	https://paperswithcode.com/paper/latent-fingerprint-recognition-role-of
Repo	https://github.com/prip-lab/MSU-LatentAFIS
Framework	pytorch

Pseudo-Random Number Generation using Generative Adversarial Networks


Title	Pseudo-Random Number Generation using Generative Adversarial Networks
Authors	Marcello De Bernardi, MHR Khouzani, Pasquale Malacaria
Abstract	Pseudo-random number generators (PRNG) are a fundamental element of many security algorithms. We introduce a novel approach to their implementation, by proposing the use of generative adversarial networks (GAN) to train a neural network to behave as a PRNG. Furthermore, we showcase a number of interesting modifications to the standard GAN architecture. The most significant is partially concealing the output of the GAN’s generator, and training the adversary to discover a mapping from the overt part to the concealed part. The generator therefore learns to produce values the adversary cannot predict, rather than to approximate an explicit reference distribution. We demonstrate that a GAN can effectively train even a small feed-forward fully connected neural network to produce pseudo-random number sequences with good statistical properties. At best, subjected to the NIST test suite, the trained generator passed around 99% of test instances and 98% of overall tests, outperforming a number of standard non-cryptographic PRNGs.
Tasks
Published	2018-09-30
URL	http://arxiv.org/abs/1810.00378v1
PDF	http://arxiv.org/pdf/1810.00378v1.pdf
PWC	https://paperswithcode.com/paper/pseudo-random-number-generation-using
Repo	https://github.com/marcellodebernardi/adversarial-csprng
Framework	tf

Provably Efficient Maximum Entropy Exploration


Title	Provably Efficient Maximum Entropy Exploration
Authors	Elad Hazan, Sham M. Kakade, Karan Singh, Abby Van Soest
Abstract	Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do? This work studies a broad class of objectives that are defined solely as functions of the state-visitation frequencies that are induced by how the agent behaves. For example, one natural, intrinsically defined, objective problem is for the agent to learn a policy which induces a distribution over state space that is as uniform as possible, which can be measured in an entropic sense. We provide an efficient algorithm to optimize such such intrinsically defined objectives, when given access to a black box planning oracle (which is robust to function approximation). Furthermore, when restricted to the tabular setting where we have sample based access to the MDP, our proposed algorithm is provably efficient, both in terms of its sample and computational complexities. Key to our algorithmic methodology is utilizing the conditional gradient method (a.k.a. the Frank-Wolfe algorithm) which utilizes an approximate MDP solver.
Tasks
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02690v2
PDF	http://arxiv.org/pdf/1812.02690v2.pdf
PWC	https://paperswithcode.com/paper/provably-efficient-maximum-entropy
Repo	https://github.com/abbyvansoest/maxent
Framework	tf

Isolating Sources of Disentanglement in Variational Autoencoders


Title	Isolating Sources of Disentanglement in Variational Autoencoders
Authors	Ricky T. Q. Chen, Xuechen Li, Roger Grosse, David Duvenaud
Abstract	We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate our $\beta$-TCVAE (Total Correlation Variational Autoencoder), a refinement of the state-of-the-art $\beta$-VAE objective for learning disentangled representations, requiring no additional hyperparameters during training. We further propose a principled classifier-free measure of disentanglement called the mutual information gap (MIG). We perform extensive quantitative and qualitative experiments, in both restricted and non-restricted settings, and show a strong relation between total correlation and disentanglement, when the latent variables model is trained using our framework.
Tasks
Published	2018-02-14
URL	http://arxiv.org/abs/1802.04942v5
PDF	http://arxiv.org/pdf/1802.04942v5.pdf
PWC	https://paperswithcode.com/paper/isolating-sources-of-disentanglement-in
Repo	https://github.com/rtqichen/beta-tcvae
Framework	pytorch

VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking


Title	VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
Authors	Quan Wang, Hannah Muckenhirn, Kevin Wilson, Prashant Sridhar, Zelin Wu, John Hershey, Rif A. Saurous, Ron J. Weiss, Ye Jia, Ignacio Lopez Moreno
Abstract	In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram masking network that takes both noisy spectrogram and speaker embedding as input, and produces a mask. Our system significantly reduces the speech recognition WER on multi-speaker signals, with minimal WER degradation on single-speaker signals.
Tasks	Speaker Recognition, Speaker Separation, Speech Enhancement, Speech Recognition
Published	2018-10-11
URL	https://arxiv.org/abs/1810.04826v6
PDF	https://arxiv.org/pdf/1810.04826v6.pdf
PWC	https://paperswithcode.com/paper/voicefilter-targeted-voice-separation-by
Repo	https://github.com/mindslab-ai/voicefilter
Framework	pytorch

Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT


Title	Generative Adversarial Networks for Image-to-Image Translation on Multi-Contrast MR Images - A Comparison of CycleGAN and UNIT
Authors	Per Welander, Simon Karlsson, Anders Eklund
Abstract	In medical imaging, a general problem is that it is costly and time consuming to collect high quality data from healthy and diseased subjects. Generative adversarial networks (GANs) is a deep learning method that has been developed for synthesizing data. GANs can thereby be used to generate more realistic training data, to improve classification performance of machine learning algorithms. Another application of GANs is image-to-image translations, e.g. generating magnetic resonance (MR) images from computed tomography (CT) images, which can be used to obtain multimodal datasets from a single modality. Here, we evaluate two unsupervised GAN models (CycleGAN and UNIT) for image-to-image translation of T1- and T2-weighted MR images, by comparing generated synthetic MR images to ground truth images. We also evaluate two supervised models; a modification of CycleGAN and a pure generator model. A small perceptual study was also performed to evaluate how visually realistic the synthesized images are. It is shown that the implemented GAN models can synthesize visually realistic MR images (incorrectly labeled as real by a human). It is also shown that models producing more visually realistic synthetic images not necessarily have better quantitative error measurements, when compared to ground truth data. Code is available at https://github.com/simontomaskarlsson/GAN-MRI
Tasks	Computed Tomography (CT), Image-to-Image Translation, Medical Image Generation
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07777v1
PDF	http://arxiv.org/pdf/1806.07777v1.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-networks-for-image-to
Repo	https://github.com/Siddhartha24795/Medical-Image-Synthesis
Framework	tf

Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation


Title	Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation
Authors	Wonwoong Cho, Sungha Choi, David Keetae Park, Inkyu Shin, Jaegul Choo
Abstract	Recently, unsupervised exemplar-based image-to-image translation, conditioned on a given exemplar without the paired data, has accomplished substantial advancements. In order to transfer the information from an exemplar to an input image, existing methods often use a normalization technique, e.g., adaptive instance normalization, that controls the channel-wise statistics of an input activation map at a particular layer, such as the mean and the variance. Meanwhile, style transfer approaches similar task to image translation by nature, demonstrated superior performance by using the higher-order statistics such as covariance among channels in representing a style. In detail, it works via whitening (given a zero-mean input feature, transforming its covariance matrix into the identity). followed by coloring (changing the covariance matrix of the whitened feature to those of the style feature). However, applying this approach in image translation is computationally intensive and error-prone due to the expensive time complexity and its non-trivial backpropagation. In response, this paper proposes an end-to-end approach tailored for image translation that efficiently approximates this transformation with our novel regularization methods. We further extend our approach to a group-wise form for memory and time efficiency as well as image quality. Extensive qualitative and quantitative experiments demonstrate that our proposed method is fast, both in training and inference, and highly effective in reflecting the style of an exemplar. Finally, our code is available at https://github.com/WonwoongCho/GDWCT.
Tasks	Image-to-Image Translation, Style Transfer
Published	2018-12-24
URL	https://arxiv.org/abs/1812.09912v2
PDF	https://arxiv.org/pdf/1812.09912v2.pdf
PWC	https://paperswithcode.com/paper/image-to-image-translation-via-group-wise
Repo	https://github.com/WonwoongCho/GDWCT
Framework	pytorch

Deep Optimisation: Solving Combinatorial Optimisation Problems using Deep Neural Networks


Title	Deep Optimisation: Solving Combinatorial Optimisation Problems using Deep Neural Networks
Authors	J. R. Caldwell, R. A. Watson, C. Thies, J. D. Knowles
Abstract	Deep Optimisation (DO) combines evolutionary search with Deep Neural Networks (DNNs) in a novel way - not for optimising a learning algorithm, but for finding a solution to an optimisation problem. Deep learning has been successfully applied to classification, regression, decision and generative tasks and in this paper we extend its application to solving optimisation problems. Model Building Optimisation Algorithms (MBOAs), a branch of evolutionary algorithms, have been successful in combining machine learning methods and evolutionary search but, until now, they have not utilised DNNs. DO is the first algorithm to use a DNN to learn and exploit the problem structure to adapt the variation operator (changing the neighbourhood structure of the search process). We demonstrate the performance of DO using two theoretical optimisation problems within the MAXSAT class. The Hierarchical Transformation Optimisation Problem (HTOP) has controllable deep structure that provides a clear evaluation of how DO works and why using a layerwise technique is essential for learning and exploiting problem structure. The Parity Modular Constraint Problem (MCparity) is a simplistic example of a problem containing higher-order dependencies (greater than pairwise) which DO can solve and state of the art MBOAs cannot. Further, we show that DO can exploit deep structure in TSP instances. Together these results show that there exists problems that DO can find and exploit deep problem structure that other algorithms cannot. Making this connection between DNNs and optimisation allows for the utilisation of advanced tools applicable to DNNs that current MBOAs are unable to use.
Tasks
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00784v1
PDF	http://arxiv.org/pdf/1811.00784v1.pdf
PWC	https://paperswithcode.com/paper/deep-optimisation-solving-combinatorial
Repo	https://github.com/JimC12/Deep-Optimisation
Framework	tf

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling


Title	Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
Authors	Liyuan Liu, Xiang Ren, Jingbo Shang, Jian Peng, Jiawei Han
Abstract	Many efforts have been made to facilitate natural language processing tasks with pre-trained language models (LMs), and brought significant improvements to various applications. To fully leverage the nearly unlimited corpora and capture linguistic information of multifarious levels, large-size LMs are required; but for a specific task, only parts of these information are useful. Such large-sized LMs, even in the inference stage, may cause heavy computation workloads, making them too time-consuming for large-scale applications. Here we propose to compress bulky LMs while preserving useful information with regard to a specific task. As different layers of the model keep different information, we develop a layer selection method for model pruning using sparsity-inducing regularization. By introducing the dense connectivity, we can detach any layer without affecting others, and stretch shallow and wide LMs to be deep and narrow. In model training, LMs are learned with layer-wise dropouts for better robustness. Experiments on two benchmark datasets demonstrate the effectiveness of our method.
Tasks	Language Modelling, Named Entity Recognition
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07827v2
PDF	http://arxiv.org/pdf/1804.07827v2.pdf
PWC	https://paperswithcode.com/paper/efficient-contextualized-representation
Repo	https://github.com/LiyuanLucasLiu/LD-Net
Framework	pytorch