January 30, 2020

3037 words 15 mins read

Paper Group ANR 342

Aspect-Sentiment Embeddings for Company Profiling and Employee Opinion Mining. Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal Grids. Categorizing Wireheading in Partially Embedded Agents. Accelerating Large-Kernel Convolution Using Summed-Area Tables. Learned Point Cloud Geometry Compression. Estimation of Muscle Fascicle Or …

Aspect-Sentiment Embeddings for Company Profiling and Employee Opinion Mining


Title	Aspect-Sentiment Embeddings for Company Profiling and Employee Opinion Mining
Authors	Rajiv Bajpai, Devamanyu Hazarika, Kunal Singh, Sruthi Gorantla, Erik Cambria, Roger Zimmerman
Abstract	With the multitude of companies and organizations abound today, ranking them and choosing one out of the many is a difficult and cumbersome task. Although there are many available metrics that rank companies, there is an inherent need for a generalized metric that takes into account the different aspects that constitute employee opinions of the companies. In this work, we aim to overcome the aforementioned problem by generating aspect-sentiment based embedding for the companies by looking into reliable employee reviews of them. We created a comprehensive dataset of company reviews from the famous website Glassdoor.com and employed a novel ensemble approach to perform aspect-level sentiment analysis. Although a relevant amount of work has been done on reviews centered on subjects like movies, music, etc., this work is the first of its kind. We also provide several insights from the collated embeddings, thus helping users gain a better understanding of their options as well as select companies using customized preferences.
Tasks	Opinion Mining, Sentiment Analysis
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08342v1
PDF	http://arxiv.org/pdf/1902.08342v1.pdf
PWC	https://paperswithcode.com/paper/aspect-sentiment-embeddings-for-company
Repo
Framework

Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal Grids


Title	Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal Grids
Authors	Daniela Ridel, Nachiket Deo, Denis Wolf, Mohan Trivedi
Abstract	Forecasting long-term human motion is a challenging task due to the non-linearity, multi-modality and inherent uncertainty in future trajectories. The underlying scene and past motion of agents can provide useful cues to predict their future motion. However, the heterogeneity of the two inputs poses a challenge for learning a joint representation of the scene and past trajectories. To address this challenge, we propose a model based on grid representations to forecast agent trajectories. We represent the past trajectories of agents using binary 2-D grids, and the underlying scene as a RGB birds-eye view (BEV) image, with an agent-centric frame of reference. We encode the scene and past trajectories using convolutional layers and generate trajectory forecasts using a Convolutional LSTM (ConvLSTM) decoder. Results on the publicly available Stanford Drone Dataset (SDD) show that our model outperforms prior approaches and outputs realistic future trajectories that comply with scene structure and past motion.
Tasks
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07507v1
PDF	https://arxiv.org/pdf/1909.07507v1.pdf
PWC	https://paperswithcode.com/paper/scene-compliant-trajectory-forecast-with
Repo
Framework

Categorizing Wireheading in Partially Embedded Agents


Title	Categorizing Wireheading in Partially Embedded Agents
Authors	Arushi Majha, Sayan Sarkar, Davide Zagami
Abstract	$\textit{Embedded agents}$ are not explicitly separated from their environment, lacking clear I/O channels. Such agents can reason about and modify their internal parts, which they are incentivized to shortcut or $\textit{wirehead}$ in order to achieve the maximal reward. In this paper, we provide a taxonomy of ways by which wireheading can occur, followed by a definition of wirehead-vulnerable agents. Starting from the fully dualistic universal agent AIXI, we introduce a spectrum of partially embedded agents and identify wireheading opportunities that such agents can exploit, experimentally demonstrating the results with the GRL simulation platform AIXIjs. We contextualize wireheading in the broader class of all misalignment problems - where the goals of the agent conflict with the goals of the human designer - and conjecture that the only other possible type of misalignment is specification gaming. Motivated by this taxonomy, we define wirehead-vulnerable agents as embedded agents that choose to behave differently from fully dualistic agents lacking access to their internal parts.
Tasks
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09136v1
PDF	https://arxiv.org/pdf/1906.09136v1.pdf
PWC	https://paperswithcode.com/paper/categorizing-wireheading-in-partially
Repo
Framework

Accelerating Large-Kernel Convolution Using Summed-Area Tables


Title	Accelerating Large-Kernel Convolution Using Summed-Area Tables
Authors	Linguang Zhang, Maciej Halber, Szymon Rusinkiewicz
Abstract	Expanding the receptive field to capture large-scale context is key to obtaining good performance in dense prediction tasks, such as human pose estimation. While many state-of-the-art fully-convolutional architectures enlarge the receptive field by reducing resolution using strided convolution or pooling layers, the most straightforward strategy is adopting large filters. This, however, is costly because of the quadratic increase in the number of parameters and multiply-add operations. In this work, we explore using learnable box filters to allow for convolution with arbitrarily large kernel size, while keeping the number of parameters per filter constant. In addition, we use precomputed summed-area tables to make the computational cost of convolution independent of the filter size. We adapt and incorporate the box filter as a differentiable module in a fully-convolutional neural network, and demonstrate its competitive performance on popular benchmarks for the task of human pose estimation.
Tasks	Pose Estimation
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11367v1
PDF	https://arxiv.org/pdf/1906.11367v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-large-kernel-convolution-using
Repo
Framework

Learned Point Cloud Geometry Compression


Title	Learned Point Cloud Geometry Compression
Authors	Jianqiang Wang, Hao Zhu, Zhan Ma, Tong Chen, Haojie Liu, Qiu Shen
Abstract	This paper presents a novel end-to-end Learned Point Cloud Geometry Compression (a.k.a., Learned-PCGC) framework, to efficiently compress the point cloud geometry (PCG) using deep neural networks (DNN) based variational autoencoders (VAE). In our approach, PCG is first voxelized, scaled and partitioned into non-overlapped 3D cubes, which is then fed into stacked 3D convolutions for compact latent feature and hyperprior generation. Hyperpriors are used to improve the conditional probability modeling of latent features. A weighted binary cross-entropy (WBCE) loss is applied in training while an adaptive thresholding is used in inference to remove unnecessary voxels and reduce the distortion. Objectively, our method exceeds the geometry-based point cloud compression (G-PCC) algorithm standardized by well-known Moving Picture Experts Group (MPEG) with a significant performance margin, e.g., at least 60% BD-Rate (Bjontegaard Delta Rate) gains, using common test datasets. Subjectively, our method has presented better visual quality with smoother surface reconstruction and appealing details, in comparison to all existing MPEG standard compliant PCC methods. Our method requires about 2.5MB parameters in total, which is a fairly small size for practical implementation, even on embedded platform. Additional ablation studies analyze a variety of aspects (e.g., cube size, kernels, etc) to explore the application potentials of our learned-PCGC.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12037v1
PDF	https://arxiv.org/pdf/1909.12037v1.pdf
PWC	https://paperswithcode.com/paper/learned-point-cloud-geometry-compression
Repo
Framework

Estimation of Muscle Fascicle Orientation in Ultrasonic Images


Title	Estimation of Muscle Fascicle Orientation in Ultrasonic Images
Authors	Regina Pohle-Fröhlich, Christoph Dalitz, Charlotte Richter, Benjamin Stäudle, Kirsten Albracht
Abstract	We compare four different algorithms for automatically estimating the muscle fascicle angle from ultrasonic images: the vesselness filter, the Radon transform, the projection profile method and the gray level cooccurence matrix (GLCM). The algorithm results are compared to ground truth data generated by three different experts on 425 image frames from two videos recorded during different types of motion. The best agreement with the ground truth data was achieved by a combination of pre-processing with a vesselness filter and measuring the angle with the projection profile method. The robustness of the estimation is increased by applying the algorithms to subregions with high gradients and performing a LOESS fit through these estimates.
Tasks
Published	2019-12-09
URL	https://arxiv.org/abs/1912.04134v1
PDF	https://arxiv.org/pdf/1912.04134v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-muscle-fascicle-orientation-in
Repo
Framework

Multi-Speaker End-to-End Speech Synthesis


Title	Multi-Speaker End-to-End Speech Synthesis
Authors	Jihyun Park, Kexin Zhao, Kainan Peng, Wei Ping
Abstract	In this work, we extend ClariNet (Ping et al., 2019), a fully end-to-end speech synthesis model (i.e., text-to-wave), to generate high-fidelity speech from multiple speakers. To model the unique characteristic of different voices, low dimensional trainable speaker embeddings are shared across each component of ClariNet and trained together with the rest of the model. We demonstrate that the multi-speaker ClariNet outperforms state-of-the-art systems in terms of naturalness, because the whole model is jointly optimized in an end-to-end manner.
Tasks	Speech Synthesis
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04462v1
PDF	https://arxiv.org/pdf/1907.04462v1.pdf
PWC	https://paperswithcode.com/paper/multi-speaker-end-to-end-speech-synthesis
Repo
Framework

LHC analysis-specific datasets with Generative Adversarial Networks


Title	LHC analysis-specific datasets with Generative Adversarial Networks
Authors	Bobak Hashemi, Nick Amin, Kaustuv Datta, Dominick Olivito, Maurizio Pierini
Abstract	Using generative adversarial networks (GANs), we investigate the possibility of creating large amounts of analysis-specific simulated LHC events at limited computing cost. This kind of generative model is analysis specific in the sense that it directly generates the high-level features used in the last stage of a given physics analyses, learning the N-dimensional distribution of relevant features in the context of a specific analysis selection. We apply this idea to the generation of muon four-momenta in $Z \to \mu\mu$ events at the LHC. We highlight how use-case specific issues emerge when the distributions of the considered quantities exhibit particular features. We show how substantial performance improvements and convergence speed-up can be obtained by including regression terms in the loss function of the generator. We develop an objective criterion to assess the geenrator performance in a quantitative way. With further development, a generalization of this approach could substantially reduce the needed amount of centrally produced fully simulated events in large particle physics experiments.
Tasks
Published	2019-01-16
URL	http://arxiv.org/abs/1901.05282v1
PDF	http://arxiv.org/pdf/1901.05282v1.pdf
PWC	https://paperswithcode.com/paper/lhc-analysis-specific-datasets-with
Repo
Framework

Stable-Predictive Optimistic Counterfactual Regret Minimization


Title	Stable-Predictive Optimistic Counterfactual Regret Minimization
Authors	Gabriele Farina, Christian Kroer, Noam Brown, Tuomas Sandholm
Abstract	The CFR framework has been a powerful tool for solving large-scale extensive-form games in practice. However, the theoretical rate at which past CFR-based algorithms converge to the Nash equilibrium is on the order of $O(T^{-1/2})$, where $T$ is the number of iterations. In contrast, first-order methods can be used to achieve a $O(T^{-1})$ dependence on iterations, yet these methods have been less successful in practice. In this work we present the first CFR variant that breaks the square-root dependence on iterations. By combining and extending recent advances on predictive and stable regret minimizers for the matrix-game setting we show that it is possible to leverage “optimistic” regret minimizers to achieve a $O(T^{-3/4})$ convergence rate within CFR. This is achieved by introducing a new notion of stable-predictivity, and by setting the stability of each counterfactual regret minimizer relative to its location in the decision tree. Experiments show that this method is faster than the original CFR algorithm, although not as fast as newer variants, in spite of their worst-case $O(T^{-1/2})$ dependence on iterations.
Tasks
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04982v1
PDF	http://arxiv.org/pdf/1902.04982v1.pdf
PWC	https://paperswithcode.com/paper/stable-predictive-optimistic-counterfactual
Repo
Framework

Towards Quality Assurance of Software Product Lines with Adversarial Configurations


Title	Towards Quality Assurance of Software Product Lines with Adversarial Configurations
Authors	Paul Temple, Mathieu Acher, Gilles Perrouin, Battista Biggio, Jean-marc Jezequel, Fabio Roli
Abstract	Software product line (SPL) engineers put a lot of effort to ensure that, through the setting of a large number of possible configuration options, products are acceptable and well-tailored to customers’ needs. Unfortunately, options and their mutual interactions create a huge configuration space which is intractable to exhaustively explore. Instead of testing all products, machine learning techniques are increasingly employed to approximate the set of acceptable products out of a small training sample of configurations. Machine learning (ML) techniques can refine a software product line through learned constraints and a priori prevent non-acceptable products to be derived. In this paper, we use adversarial ML techniques to generate adversarial configurations fooling ML classifiers and pinpoint incorrect classifications of products (videos) derived from an industrial video generator. Our attacks yield (up to) a 100% misclassification rate and a drop in accuracy of 5%. We discuss the implications these results have on SPL quality assurance.
Tasks
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07283v1
PDF	https://arxiv.org/pdf/1909.07283v1.pdf
PWC	https://paperswithcode.com/paper/towards-quality-assurance-of-software-product
Repo
Framework

Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification


Title	Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification
Authors	Yichao Zhou, Jyun-Yu Jiang, Kai-Wei Chang, Wei Wang
Abstract	Adversarial attacks against machine learning models have threatened various real-world applications such as spam filtering and sentiment analysis. In this paper, we propose a novel framework, learning to DIScriminate Perturbations (DISP), to identify and adjust malicious perturbations, thereby blocking adversarial attacks for text classification models. To identify adversarial attacks, a perturbation discriminator validates how likely a token in the text is perturbed and provides a set of potential perturbations. For each potential perturbation, an embedding estimator learns to restore the embedding of the original word based on the context and a replacement token is chosen based on approximate kNN search. DISP can block adversarial attacks for any NLP model without modifying the model structure or training procedure. Extensive experiments on two benchmark datasets demonstrate that DISP significantly outperforms baseline methods in blocking adversarial attacks for text classification. In addition, in-depth analysis shows the robustness of DISP across different situations.
Tasks	Sentiment Analysis, Text Classification
Published	2019-09-06
URL	https://arxiv.org/abs/1909.03084v1
PDF	https://arxiv.org/pdf/1909.03084v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-discriminate-perturbations-for
Repo
Framework

A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation


Title	A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation
Authors	Hieu-Thi Luong, Junichi Yamagishi
Abstract	By representing speaker characteristic as a single fixed-length vector extracted solely from speech, we can train a neural multi-speaker speech synthesis model by conditioning the model on those vectors. This model can also be adapted to unseen speakers regardless of whether the transcript of adaptation data is available or not. However, this setup restricts the speaker component to just a single bias vector, which in turn limits the performance of adaptation process. In this study, we propose a novel speech synthesis model, which can be adapted to unseen speakers by fine-tuning part of or all of the network using either transcribed or untranscribed speech. Our methodology essentially consists of two steps: first, we split the conventional acoustic model into a speaker-independent (SI) linguistic encoder and a speaker-adaptive (SA) acoustic decoder; second, we train an auxiliary acoustic encoder that can be used as a substitute for the linguistic encoder whenever linguistic features are unobtainable. The results of objective and subjective evaluations show that adaptation using either transcribed or untranscribed speech with our methodology achieved a reasonable level of performance with an extremely limited amount of data and greatly improved performance with more data. Surprisingly, adaptation with untranscribed speech surpassed the transcribed counterpart in the subjective test, which reveals the limitations of the conventional acoustic model and hints at potential directions for improvements.
Tasks	Speech Synthesis
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07414v2
PDF	https://arxiv.org/pdf/1906.07414v2.pdf
PWC	https://paperswithcode.com/paper/a-unified-speaker-adaptation-method-for
Repo
Framework

Dont Even Look Once: Synthesizing Features for Zero-Shot Detection


Title	Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
Authors	Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama
Abstract	Zero-shot detection, namely, localizing both seen and unseen objects, increasingly gains importance for large-scale applications, with large number of object classes, since, collecting sufficient annotated data with ground truth bounding boxes is simply not scalable. While vanilla deep neural networks deliver high performance for objects available during training, unseen object detection degrades significantly. At a fundamental level, while vanilla detectors are capable of proposing bounding boxes, which include unseen objects, they are often incapable of assigning high-confidence to unseen objects, due to the inherent precision/recall tradeoffs that requires rejecting background objects. We propose a novel detection algorithm Dont Even Look Once (DELO), that synthesizes visual features for unseen objects and augments existing training algorithms to incorporate unseen object detection. Our proposed scheme is evaluated on Pascal VOC and MSCOCO, and we demonstrate significant improvements in test accuracy over vanilla and other state-of-art zero-shot detectors
Tasks	Object Detection
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07933v2
PDF	https://arxiv.org/pdf/1911.07933v2.pdf
PWC	https://paperswithcode.com/paper/dont-even-look-once-synthesizing-features-for
Repo
Framework

Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning


Title	Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning
Authors	Igor Colin, Ludovic Dos Santos, Kevin Scaman
Abstract	We investigate the theoretical limits of pipeline parallel learning of deep learning architectures, a distributed setup in which the computation is distributed per layer instead of per example. For smooth convex and non-convex objective functions, we provide matching lower and upper complexity bounds and show that a naive pipeline parallelization of Nesterov’s accelerated gradient descent is optimal. For non-smooth convex functions, we provide a novel algorithm coined Pipeline Parallel Random Smoothing (PPRS) that is within a $d^{1/4}$ multiplicative factor of the optimal convergence rate, where $d$ is the underlying dimension. While the convergence rate still obeys a slow $\varepsilon^{-2}$ convergence rate, the depth-dependent part is accelerated, resulting in a near-linear speed-up and convergence time that only slightly depends on the depth of the deep learning architecture. Finally, we perform an empirical analysis of the non-smooth non-convex case and show that, for difficult and highly non-smooth problems, PPRS outperforms more traditional optimization algorithms such as gradient descent and Nesterov’s accelerated gradient descent for problems where the sample size is limited, such as few-shot or adversarial learning.
Tasks
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05104v1
PDF	https://arxiv.org/pdf/1910.05104v1.pdf
PWC	https://paperswithcode.com/paper/theoretical-limits-of-pipeline-parallel
Repo
Framework

Simultaneous lesion and neuroanatomy segmentation in Multiple Sclerosis using deep neural networks


Title	Simultaneous lesion and neuroanatomy segmentation in Multiple Sclerosis using deep neural networks
Authors	Richard McKinley, Rik Wepfer, Fabian Aschwanden, Lorenz Grunder, Raphaela Muri, Christian Rummel, Rajeev Verma, Christian Weisstanner, Mauricio Reyes, Anke Salmen, Andrew Chan, Franca Wagner, Roland Wiest
Abstract	Segmentation of both white matter lesions and deep grey matter structures is an important task in the quantification of magnetic resonance imaging in multiple sclerosis. Typically these tasks are performed separately: in this paper we present a single segmentation solution based on convolutional neural networks (CNNs) for providing fast, reliable segmentations of multimodal magnetic resonance images into lesion classes and normal-appearing grey- and white-matter structures. We show substantial, statistically significant improvements in both Dice coefficient and in lesion-wise specificity and sensitivity, compared to previous approaches, and agreement with individual human raters in the range of human inter-rater variability. The method is trained on data gathered from a single centre: nonetheless, it performs well on data from centres, scanners and field-strengths not represented in the training dataset. A retrospective study found that the classifier successfully identified lesions missed by the human raters. Lesion labels were provided by human raters, while weak labels for other brain structures (including CSF, cortical grey matter, cortical white matter, cerebellum, amygdala, hippocampus, subcortical GM structures and choroid plexus) were provided by Freesurfer 5.3. The segmentations of these structures compared well, not only with Freesurfer 5.3, but also with FSL-First and Freesurfer 6.0.
Tasks
Published	2019-01-22
URL	https://arxiv.org/abs/1901.07419v2
PDF	https://arxiv.org/pdf/1901.07419v2.pdf
PWC	https://paperswithcode.com/paper/simultaneous-lesion-and-neuroanatomy
Repo
Framework