January 30, 2020

3115 words 15 mins read

Paper Group ANR 417

Improving Natural Language Inference with a Pretrained Parser. A Categorisation of Post-hoc Explanations for Predictive Models. Low-Cost Outdoor Air Quality Monitoring and In-Field Sensor Calibration. A Time Series Analysis of Emotional Loading in Central Bank Statements. Divide and Conquer: an Accurate Machine Learning Algorithm to Process Split V …

Improving Natural Language Inference with a Pretrained Parser


Title	Improving Natural Language Inference with a Pretrained Parser
Authors	Deric Pang, Lucy H. Lin, Noah A. Smith
Abstract	We introduce a novel approach to incorporate syntax into natural language inference (NLI) models. Our method uses contextual token-level vector representations from a pretrained dependency parser. Like other contextual embedders, our method is broadly applicable to any neural model. We experiment with four strong NLI models (decomposable attention model, ESIM, BERT, and MT-DNN), and show consistent benefit to accuracy across three NLI benchmarks.
Tasks	Natural Language Inference
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08217v1
PDF	https://arxiv.org/pdf/1909.08217v1.pdf
PWC	https://paperswithcode.com/paper/improving-natural-language-inference-with-a
Repo
Framework

A Categorisation of Post-hoc Explanations for Predictive Models


Title	A Categorisation of Post-hoc Explanations for Predictive Models
Authors	John Mitros, Brian Mac Namee
Abstract	The ubiquity of machine learning based predictive models in modern society naturally leads people to ask how trustworthy those models are? In predictive modeling, it is quite common to induce a trade-off between accuracy and interpretability. For instance, doctors would like to know how effective some treatment will be for a patient or why the model suggested a particular medication for a patient exhibiting those symptoms? We acknowledge that the necessity for interpretability is a consequence of an incomplete formalisation of the problem, or more precisely of multiple meanings adhered to a particular concept. For certain problems, it is not enough to get the answer (what), the model also has to provide an explanation of how it came to that conclusion (why), because a correct prediction, only partially solves the original problem. In this article we extend existing categorisation of techniques to aid model interpretability and test this categorisation.
Tasks
Published	2019-04-04
URL	http://arxiv.org/abs/1904.02495v1
PDF	http://arxiv.org/pdf/1904.02495v1.pdf
PWC	https://paperswithcode.com/paper/a-categorisation-of-post-hoc-explanations-for
Repo
Framework

Low-Cost Outdoor Air Quality Monitoring and In-Field Sensor Calibration


Title	Low-Cost Outdoor Air Quality Monitoring and In-Field Sensor Calibration
Authors	Francesco Concas, Julien Mineraud, Eemil Lagerspetz, Samu Varjonen, Kai Puolamäki, Petteri Nurmi, Sasu Tarkoma
Abstract	The significance of air pollution and problems associated with it is fueling deployments of air quality monitoring stations worldwide. The most common approach for air quality monitoring is to rely on environmental monitoring stations, which unfortunately are very expensive both to acquire and to maintain. Hence, environmental monitoring stations typically are deployed sparsely, resulting in limited spatial resolution for measurements. Recently, low-cost air quality sensors have emerged as an alternative that can improve granularity of monitoring. The use of low-cost air quality sensors, however, presents several challenges: they suffer from cross-sensitivities between different ambient pollutants; they can be affected by external factors such as traffic, weather changes, and human behavior; and their accuracy degrades over time. The accuracy of low-cost sensors can be improved through periodic re-calibration with particularly machine learning based calibration having shown great promise due to its capability to calibrate sensors in-field. In this article, we survey the rapidly growing research landscape of low-cost sensor technologies for air quality monitoring, and their calibration using machine learning techniques. We also identify open research challenges and present directions for future research.
Tasks	Calibration
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06384v2
PDF	https://arxiv.org/pdf/1912.06384v2.pdf
PWC	https://paperswithcode.com/paper/a-gap-analysis-of-low-cost-outdoor-air
Repo
Framework

A Time Series Analysis of Emotional Loading in Central Bank Statements


Title	A Time Series Analysis of Emotional Loading in Central Bank Statements
Authors	Sven Buechel, Simon Junker, Thore Schlaak, Claus Michelsen, Udo Hahn
Abstract	We examine the affective content of central bank press statements using emotion analysis. Our focus is on two major international players, the European Central Bank (ECB) and the US Federal Reserve Bank (Fed), covering a time span from 1998 through 2019. We reveal characteristic patterns in the emotional dimensions of valence, arousal, and dominance and find—despite the commonly established attitude that emotional wording in central bank communication should be avoided—a correlation between the state of the economy and particularly the dominance dimension in the press releases under scrutiny and, overall, an impact of the president in office.
Tasks	Emotion Recognition, Time Series, Time Series Analysis
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11522v1
PDF	https://arxiv.org/pdf/1911.11522v1.pdf
PWC	https://paperswithcode.com/paper/a-time-series-analysis-of-emotional-loading-1
Repo
Framework

Divide and Conquer: an Accurate Machine Learning Algorithm to Process Split Videos on a Parallel Processing Infrastructure


Title	Divide and Conquer: an Accurate Machine Learning Algorithm to Process Split Videos on a Parallel Processing Infrastructure
Authors	Walter M. Mayor Toro, Juan C. Perafan Villota, Oscar H. Mondragon, Johan S. Obando Ceron
Abstract	Every day the number of traffic cameras in cities rapidly increase and huge amount of video data are generated. Parallel processing infrastruture, such as Hadoop, and programming models, such as MapReduce, are being used to promptly process that amount of data. The common approach for video processing by using Hadoop MapReduce is to process an entire video on only one node, however, in order to avoid parallelization problems, such as load imbalance, we propose to process videos by splitting it into equal parts and processing each resulting chunk on a different node. We used some machine learning techniques to detect and track the vehicles. However, video division may produce inaccurate results. To solve this problem we proposed a heuristic algorithm to avoid process a vehicle in more than one chunk.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09601v1
PDF	https://arxiv.org/pdf/1912.09601v1.pdf
PWC	https://paperswithcode.com/paper/divide-and-conquer-an-accurate-machine
Repo
Framework

Efficient Network Construction through Structural Plasticity


Title	Efficient Network Construction through Structural Plasticity
Authors	Xiaocong Du, Zheng Li, Yufei Ma, Yu Cao
Abstract	Deep Neural Networks (DNNs) on hardware is facing excessive computation cost due to the massive number of parameters. A typical training pipeline to mitigate over-parameterization is to pre-define a DNN structure first with redundant learning units (filters and neurons) under the goal of high accuracy, then to prune redundant learning units after training with the purpose of efficient inference. We argue that it is sub-optimal to introduce redundancy into training for the purpose of reducing redundancy later in inference. Moreover, the fixed network structure further results in poor adaption to dynamic tasks, such as lifelong learning. In contrast, structural plasticity plays an indispensable role in mammalian brains to achieve compact and accurate learning. Throughout the lifetime, active connections are continuously created while those no longer important are degenerated. Inspired by such observation, we propose a training scheme, namely Continuous Growth and Pruning (CGaP), where we start the training from a small network seed, then literally execute continuous growth by adding important learning units and finally prune secondary ones for efficient inference. The inference model generated from CGaP is sparse in the structure, largely decreasing the inference power and latency when deployed on hardware platforms. With popular DNN structures on representative datasets, the efficacy of CGaP is benchmarked by both algorithm simulation and architectural modeling on Field-programmable Gate Arrays (FPGA). For example, CGaP decreases the FLOPs, model size, DRAM access energy and inference latency by 63.3%, 64.0%, 11.8% and 40.2%, respectively, for ResNet-110 on CIFAR-10.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11530v3
PDF	https://arxiv.org/pdf/1905.11530v3.pdf
PWC	https://paperswithcode.com/paper/efficient-network-construction-through
Repo
Framework

Realistic Hair Simulation Using Image Blending


Title	Realistic Hair Simulation Using Image Blending
Authors	Mohamed Attia, Mohammed Hossny, Saeid Nahavandi, Anousha Yazdabadi, Hamed Asadi
Abstract	In this presented work, we propose a realistic hair simulator using image blending for dermoscopic images. This hair simulator can be used for benchmarking and validation of the hair removal methods and in data augmentation for improving computer aided diagnostic tools. We adopted one of the popular implementation of image blending to superimpose realistic hair masks to hair lesion. This method was able to produce realistic hair masks according to a predefined mask for hair. Thus, the produced hair images and masks can be used as ground truth for hair segmentation and removal methods by inpainting hair according to a pre-defined hair masks on hairfree areas. Also, we achieved a realism score equals to 1.65 in comparison to 1.59 for the state-of-the-art hair simulator.
Tasks	Data Augmentation
Published	2019-04-19
URL	http://arxiv.org/abs/1904.09169v1
PDF	http://arxiv.org/pdf/1904.09169v1.pdf
PWC	https://paperswithcode.com/paper/realistic-hair-simulation-using-image
Repo
Framework

Stereoscopic Omnidirectional Image Quality Assessment Based on Predictive Coding Theory


Title	Stereoscopic Omnidirectional Image Quality Assessment Based on Predictive Coding Theory
Authors	Zhibo Chen, Jiahua Xu, Chaoyi Lin, Wei Zhou
Abstract	Objective quality assessment of stereoscopic omnidirectional images is a challenging problem since it is influenced by multiple aspects such as projection deformation, field of view (FoV) range, binocular vision, visual comfort, etc. Existing studies show that classic 2D or 3D image quality assessment (IQA) metrics are not able to perform well for stereoscopic omnidirectional images. However, very few research works have focused on evaluating the perceptual visual quality of omnidirectional images, especially for stereoscopic omnidirectional images. In this paper, based on the predictive coding theory of the human vision system (HVS), we propose a stereoscopic omnidirectional image quality evaluator (SOIQE) to cope with the characteristics of 3D 360-degree images. Two modules are involved in SOIQE: predictive coding theory based binocular rivalry module and multi-view fusion module. In the binocular rivalry module, we introduce predictive coding theory to simulate the competition between high-level patterns and calculate the similarity and rivalry dominance to obtain the quality scores of viewport images. Moreover, we develop the multi-view fusion module to aggregate the quality scores of viewport images with the help of both content weight and location weight. The proposed SOIQE is a parametric model without necessary of regression learning, which ensures its interpretability and generalization performance. Experimental results on our published stereoscopic omnidirectional image quality assessment database (SOLID) demonstrate that our proposed SOIQE method outperforms state-of-the-art metrics. Furthermore, we also verify the effectiveness of each proposed module on both public stereoscopic image datasets and panoramic image datasets.
Tasks	Image Quality Assessment
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05165v1
PDF	https://arxiv.org/pdf/1906.05165v1.pdf
PWC	https://paperswithcode.com/paper/stereoscopic-omnidirectional-image-quality
Repo
Framework

Tensor Restricted Isometry Property Analysis For a Large Class of Random Measurement Ensembles


Title	Tensor Restricted Isometry Property Analysis For a Large Class of Random Measurement Ensembles
Authors	Feng Zhang, Wendong Wang, Jingyao Hou, Jianjun Wang, Jianwen Huang
Abstract	In previous work, theoretical analysis based on the tensor Restricted Isometry Property (t-RIP) established the robust recovery guarantees of a low-tubal-rank tensor. The obtained sufficient conditions depend strongly on the assumption that the linear measurement maps satisfy the t-RIP. In this paper, by exploiting the probabilistic arguments, we prove that such linear measurement maps exist under suitable conditions on the number of measurements in terms of the tubal rank r and the size of third-order tensor n1, n2, n3. And the obtained minimal possible number of linear measurements is nearly optimal compared with the degrees of freedom of a tensor with tubal rank r. Specially, we consider a random sub-Gaussian distribution that includes Gaussian, Bernoulli and all bounded distributions and construct a large class of linear maps that satisfy a t-RIP with high probability. Moreover, the validity of the required number of measurements is verified by numerical experiments.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01198v2
PDF	https://arxiv.org/pdf/1906.01198v2.pdf
PWC	https://paperswithcode.com/paper/tensor-restricted-isometry-property-analysis
Repo
Framework

Confidence Trigger Detection: An Approach to Build Real-time Tracking-by-detection System


Title	Confidence Trigger Detection: An Approach to Build Real-time Tracking-by-detection System
Authors	Zhicheng Ding, Edward Wong
Abstract	With deep learning based image analysis getting popular in recent years, a lot of multiple objects tracking applications are in demand. Some of these applications (e.g., surveillance camera, intelligent robotics, and autonomous driving) require the system runs in real-time. Though recent proposed methods reach fairly high accuracy, the speed is still slower than real-time application requirement. In order to increase tracking-by-detection system’s speed for real-time tracking, we proposed confidence trigger detection (CTD) approach which uses confidence of tracker to decide when to trigger object detection. Using this approach, system can safely skip detection of images frames that objects barely move. We had studied the influence of different confidences in three popular detectors separately. Though we found trade-off between speed and accuracy, our approach reaches higher accuracy at given speed.
Tasks	Autonomous Driving, Object Detection
Published	2019-02-02
URL	http://arxiv.org/abs/1902.00615v1
PDF	http://arxiv.org/pdf/1902.00615v1.pdf
PWC	https://paperswithcode.com/paper/confidence-trigger-detection-an-approach-to
Repo
Framework

Towards Document Image Quality Assessment: A Text Line Based Framework and A Synthetic Text Line Image Dataset


Title	Towards Document Image Quality Assessment: A Text Line Based Framework and A Synthetic Text Line Image Dataset
Authors	Hongyu Li, Fan Zhu, Junhua Qiu
Abstract	Since the low quality of document images will greatly undermine the chances of success in automatic text recognition and analysis, it is necessary to assess the quality of document images uploaded in online business process, so as to reject those images of low quality. In this paper, we attempt to achieve document image quality assessment and our contributions are twofold. Firstly, since document image quality assessment is more interested in text, we propose a text line based framework to estimate document image quality, which is composed of three stages: text line detection, text line quality prediction, and overall quality assessment. Text line detection aims to find potential text lines with a detector. In the text line quality prediction stage, the quality score is computed for each text line with a CNN-based prediction model. The overall quality of document images is finally assessed with the ensemble of all text line quality. Secondly, to train the prediction model, a large-scale dataset, comprising 52,094 text line images, is synthesized with diverse attributes. For each text line image, a quality label is computed with a piece-wise function. To demonstrate the effectiveness of the proposed framework, comprehensive experiments are evaluated on two popular document image quality assessment benchmarks. Our framework significantly outperforms the state-of-the-art methods by large margins on the large and complicated dataset.
Tasks	Image Quality Assessment
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01907v1
PDF	https://arxiv.org/pdf/1906.01907v1.pdf
PWC	https://paperswithcode.com/paper/towards-document-image-quality-assessment-a
Repo
Framework

Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysis


Title	Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysis
Authors	Zelin Xiao, Hongxin Lin, Renjie Li, Hongyang Chao, Shengyong Ding
Abstract	In this paper, we propose a simple yet effective method to endow deep 3D models with rotation invariance by expressing the coordinates in an intrinsic frame determined by the object shape itself. Key to our approach is to find such an intrinsic frame which should be unique to the identical object shape and consistent across different instances of the same category, e.g. the frame axes of desks should be all roughly along the edges. Interestingly, the principal component analysis exactly provides an effective way to define such a frame, i.e. setting the principal components as the frame axes. As the principal components have direction ambiguity caused by the sign-ambiguity of eigenvector computation, there exist several intrinsic frames for each object. In order to achieve absolute rotation invariance for a deep model, we adopt the coordinates expressed in all intrinsic frames as inputs to obtain multiple output features, which will be further aggregated as a final feature via a self-attention module. Our method is theoretically rotation-invariant and can be flexibly embedded into the current network architectures. Comprehensive experiments demonstrate that our approach can achieve near state-of-the-art performance on rotation-augmented dataset for ModelNet40 classification and outperform other models on SHREC’17 perturbed retrieval task.
Tasks
Published	2019-10-20
URL	https://arxiv.org/abs/1910.08901v1
PDF	https://arxiv.org/pdf/1910.08901v1.pdf
PWC	https://paperswithcode.com/paper/endowing-deep-3d-models-with-rotation
Repo
Framework

Optimistic optimization of a Brownian


Title	Optimistic optimization of a Brownian
Authors	Jean-Bastien Grill, Michal Valko, Rémi Munos
Abstract	We address the problem of optimizing a Brownian motion. We consider a (random) realization $W$ of a Brownian motion with input space in $[0,1]$. Given $W$, our goal is to return an $\epsilon$-approximation of its maximum using the smallest possible number of function evaluations, the sample complexity of the algorithm. We provide an algorithm with sample complexity of order $\log^2(1/\epsilon)$. This improves over previous results of Al-Mharmah and Calvin (1996) and Calvin et al. (2017) which provided only polynomial rates. Our algorithm is adaptive—each query depends on previous values—and is an instance of the optimism-in-the-face-of-uncertainty principle.
Tasks
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04884v1
PDF	http://arxiv.org/pdf/1901.04884v1.pdf
PWC	https://paperswithcode.com/paper/optimistic-optimization-of-a-brownian
Repo
Framework

Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving


Title	Real-time Joint Object Detection and Semantic Segmentation Network for Automated Driving
Authors	Ganesh Sistu, Isabelle Leang, Senthil Yogamani
Abstract	Convolutional Neural Networks (CNN) are successfully used for various visual perception tasks including bounding box object detection, semantic segmentation, optical flow, depth estimation and visual SLAM. Generally these tasks are independently explored and modeled. In this paper, we present a joint multi-task network design for learning object detection and semantic segmentation simultaneously. The main motivation is to achieve real-time performance on a low power embedded SOC by sharing of encoder for both the tasks. We construct an efficient architecture using a small ResNet10 like encoder which is shared for both decoders. Object detection uses YOLO v2 like decoder and semantic segmentation uses FCN8 like decoder. We evaluate the proposed network in two public datasets (KITTI, Cityscapes) and in our private fisheye camera dataset, and demonstrate that joint network provides the same accuracy as that of separate networks. We further optimize the network to achieve 30 fps for 1280x384 resolution image.
Tasks	Depth Estimation, Object Detection, Optical Flow Estimation, Semantic Segmentation
Published	2019-01-12
URL	http://arxiv.org/abs/1901.03912v1
PDF	http://arxiv.org/pdf/1901.03912v1.pdf
PWC	https://paperswithcode.com/paper/real-time-joint-object-detection-and-semantic
Repo
Framework

Pose Guided Fashion Image Synthesis Using Deep Generative Model


Title	Pose Guided Fashion Image Synthesis Using Deep Generative Model
Authors	Wei Sun, Jawadul H. Bappy, Shanglin Yang, Yi Xu, Tianfu Wu, Hui Zhou
Abstract	Generating a photorealistic image with intended human pose is a promising yet challenging research topic for many applications such as smart photo editing, movie making, virtual try-on, and fashion display. In this paper, we present a novel deep generative model to transfer an image of a person from a given pose to a new pose while keeping fashion item consistent. In order to formulate the framework, we employ one generator and two discriminators for image synthesis. The generator includes an image encoder, a pose encoder and a decoder. The two encoders provide good representation of visual and geometrical context which will be utilized by the decoder in order to generate a photorealistic image. Unlike existing pose-guided image generation models, we exploit two discriminators to guide the synthesis process where one discriminator differentiates between generated image and real images (training samples), and another discriminator verifies the consistency of appearance between a target pose and a generated image. We perform end-to-end training of the network to learn the parameters through back-propagation given ground-truth images. The proposed generative model is capable of synthesizing a photorealistic image of a person given a target pose. We have demonstrated our results by conducting rigorous experiments on two data sets, both quantitatively and qualitatively.
Tasks	Image Generation, Pose-Guided Image Generation
Published	2019-06-17
URL	https://arxiv.org/abs/1906.07251v2
PDF	https://arxiv.org/pdf/1906.07251v2.pdf
PWC	https://paperswithcode.com/paper/pose-guided-fashion-image-synthesis-using
Repo
Framework