October 17, 2019

3583 words 17 mins read

Paper Group ANR 794

PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection. On Strengthening the Logic of Iterated Belief Revision: Proper Ordinal Interval Operators. Predicting Electric Vehicle Charging Station Usage: Using Machine Learning to Estimate Individual Station Statistics from Physical Configurations of Charging Station Networks. …

PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection


Title	PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection
Authors	Nian Liu, Junwei Han, Ming-Hsuan Yang
Abstract	In saliency detection, every pixel needs contextual information to make saliency prediction. Previous models usually incorporate contexts holistically. However, for each pixel, usually only part of its context region is useful and contributes to its prediction, while some other part may serve as noises and distractions. In this paper, we propose a novel pixel-wise contextual attention network, \ie PiCANet, to learn to selectively attend to informative context locations at each pixel. Specifically, PiCANet generates an attention map over the context region of each pixel, where each attention weight corresponds to the relevance of a context location w.r.t the referred pixel. Then, attentive contextual features can be constructed via selectively incorporating the features of useful context locations with the learned attention. We propose three specific formulations of the PiCANet via embedding the pixel-wise contextual attention mechanism into the pooling and convolution operations with attending to global or local contexts. All the three models are fully differentiable and can be integrated with CNNs with joint training. We introduce the proposed PiCANets into a U-Net architecture for salient object detection. Experimental results indicate that the proposed PiCANets can significantly improve the saliency detection performance. The generated global and local attention can learn to incorporate global contrast and smoothness, respectively, which help localize salient objects more accurately and highlight them more uniformly. Consequently, our saliency model performs favorably against other state-of-the-art methods. Moreover, we also validate that PiCANets can also improve semantic segmentation and object detection performances, which further demonstrates their effectiveness and generalization ability.
Tasks	Object Detection, Saliency Detection, Saliency Prediction, Salient Object Detection, Semantic Segmentation
Published	2018-12-15
URL	http://arxiv.org/abs/1812.06314v1
PDF	http://arxiv.org/pdf/1812.06314v1.pdf
PWC	https://paperswithcode.com/paper/picanet-pixel-wise-contextual-attention
Repo
Framework

On Strengthening the Logic of Iterated Belief Revision: Proper Ordinal Interval Operators


Title	On Strengthening the Logic of Iterated Belief Revision: Proper Ordinal Interval Operators
Authors	Richard Booth, Jake Chandler
Abstract	Darwiche and Pearl’s seminal 1997 article outlined a number of baseline principles for a logic of iterated belief revision. These principles, the DP postulates, have been supplemented in a number of alternative ways. Most of the suggestions made have resulted in a form of `reductionism' that identifies belief states with orderings of worlds. However, this position has recently been criticised as being unacceptably strong. Other proposals, such as the popular principle (P), aka` Independence’, characteristic of admissible' revision operators, remain commendably more modest. In this paper, we supplement both the DP postulates and (P) with a number of novel conditions. While the DP postulates constrain the relation between a prior and a posterior conditional belief set, our new principles notably govern the relation between two posterior conditional belief sets obtained from a common prior by different revisions. We show that operators from the resulting family, which subsumes both lexicographic and restrained revision, can be represented as relating belief states that are associated with a proper ordinal interval’ (POI) assignment, a structure more fine-grained than a simple ordering of worlds. We close the paper by noting that these operators satisfy iterated versions of a large number of AGM era postulates, including Superexpansion, that are not sound for admissible operators in general.
Tasks
Published	2018-07-26
URL	http://arxiv.org/abs/1807.09942v1
PDF	http://arxiv.org/pdf/1807.09942v1.pdf
PWC	https://paperswithcode.com/paper/on-strengthening-the-logic-of-iterated-belief
Repo
Framework

Predicting Electric Vehicle Charging Station Usage: Using Machine Learning to Estimate Individual Station Statistics from Physical Configurations of Charging Station Networks


Title	Predicting Electric Vehicle Charging Station Usage: Using Machine Learning to Estimate Individual Station Statistics from Physical Configurations of Charging Station Networks
Authors	Anshul Ramachandran, Ashwin Balakrishna, Peter Kundzicz, Anirudh Neti
Abstract	Electric vehicles (EVs) have been gaining popularity due to their environmental friendliness and efficiency. EV charging station networks are scalable solutions for supporting increasing numbers of EVs within modern electric grid constraints, yet few tools exist to aid the physical configuration design of new networks. We use neural networks to predict individual charging station usage statistics from the station’s physical location within a network. We have shown this quickly gives accurate estimates of average usage statistics given a proposed configuration, without the need for running many computationally expensive simulations. The trained neural network can help EV charging network designers rapidly test various placements of charging stations under additional individual constraints in order to find an optimal configuration given their design objectives.
Tasks
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00714v1
PDF	http://arxiv.org/pdf/1804.00714v1.pdf
PWC	https://paperswithcode.com/paper/predicting-electric-vehicle-charging-station
Repo
Framework


Title	End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perception
Authors	Zhengyuan Yang, Yixuan Zhang, Jerry Yu, Junjie Cai, Jiebo Luo
Abstract	Convolutional Neural Networks (CNN) have been successfully applied to autonomous driving tasks, many in an end-to-end manner. Previous end-to-end steering control methods take an image or an image sequence as the input and directly predict the steering angle with CNN. Although single task learning on steering angles has reported good performances, the steering angle alone is not sufficient for vehicle control. In this work, we propose a multi-task learning framework to predict the steering angle and speed control simultaneously in an end-to-end manner. Since it is nontrivial to predict accurate speed values with only visual inputs, we first propose a network to predict discrete speed commands and steering angles with image sequences. Moreover, we propose a multi-modal multi-task network to predict speed values and steering angles by taking previous feedback speeds and visual recordings as inputs. Experiments are conducted on the public Udacity dataset and a newly collected SAIC dataset. Results show that the proposed model predicts steering angles and speed values accurately. Furthermore, we improve the failure data synthesis methods to solve the problem of error accumulation in real road tests.
Tasks	Autonomous Driving, Multi-Task Learning, Self-Driving Cars, Steering Control
Published	2018-01-20
URL	http://arxiv.org/abs/1801.06734v2
PDF	http://arxiv.org/pdf/1801.06734v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-multi-modal-multi-task-vehicle
Repo
Framework


Title	Residualized Factor Adaptation for Community Social Media Prediction Tasks
Authors	Mohammadzaman Zamani, H. Andrew Schwartz, Veronica E. Lynn, Salvatore Giorgi, Niranjan Balasubramanian
Abstract	Predictive models over social media language have shown promise in capturing community outcomes, but approaches thus far largely neglect the socio-demographic context (e.g. age, education rates, race) of the community from which the language originates. For example, it may be inaccurate to assume people in Mobile, Alabama, where the population is relatively older, will use words the same way as those from San Francisco, where the median age is younger with a higher rate of college education. In this paper, we present residualized factor adaptation, a novel approach to community prediction tasks which both (a) effectively integrates community attributes, as well as (b) adapts linguistic features to community attributes (factors). We use eleven demographic and socioeconomic attributes, and evaluate our approach over five different community-level predictive tasks, spanning health (heart disease mortality, percent fair/poor health), psychology (life satisfaction), and economics (percent housing price increase, foreclosure rate). Our evaluation shows that residualized factor adaptation significantly improves 4 out of 5 community-level outcome predictions over prior state-of-the-art for incorporating socio-demographic contexts.
Tasks
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09479v1
PDF	http://arxiv.org/pdf/1808.09479v1.pdf
PWC	https://paperswithcode.com/paper/residualized-factor-adaptation-for-community
Repo
Framework

Model compression for faster structural separation of macromolecules captured by Cellular Electron Cryo-Tomography


Title	Model compression for faster structural separation of macromolecules captured by Cellular Electron Cryo-Tomography
Authors	Jialiang Guo, Bo Zhou, Xiangrui Zeng, Zachary Freyberg, Min Xu
Abstract	Electron Cryo-Tomography (ECT) enables 3D visualization of macromolecule structure inside single cells. Macromolecule classification approaches based on convolutional neural networks (CNN) were developed to separate millions of macromolecules captured from ECT systematically. However, given the fast accumulation of ECT data, it will soon become necessary to use CNN models to efficiently and accurately separate substantially more macromolecules at the prediction stage, which requires additional computational costs. To speed up the prediction, we compress classification models into compact neural networks with little in accuracy for deployment. Specifically, we propose to perform model compression through knowledge distillation. Firstly, a complex teacher network is trained to generate soft labels with better classification feasibility followed by training of customized student networks with simple architectures using the soft label to compress model complexity. Our tests demonstrate that our compressed models significantly reduce the number of parameters and time cost while maintaining similar classification accuracy.
Tasks	Model Compression
Published	2018-01-31
URL	http://arxiv.org/abs/1801.10597v1
PDF	http://arxiv.org/pdf/1801.10597v1.pdf
PWC	https://paperswithcode.com/paper/model-compression-for-faster-structural
Repo
Framework

An IoT Analytics Embodied Agent Model based on Context-Aware Machine Learning


Title	An IoT Analytics Embodied Agent Model based on Context-Aware Machine Learning
Authors	Nathalia Nascimento, Paulo Alencar, Carlos Lucena, Donald Cowan
Abstract	Agent-based Internet of Things (IoT) applications have recently emerged as applications that can involve sensors, wireless devices, machines and software that can exchange data and be accessed remotely. Such applications have been proposed in several domains including health care, smart cities and agriculture. However, despite their increased adoption, deploying these applications in specific settings has been very challenging because of the complex static and dynamic variability of the physical devices such as sensors and actuators, the software application behavior and the environment in which the application is embedded. In this paper, we propose a modeling approach for IoT analytics based on learning embodied agents (i.e. situated agents). The approach involves: (i) a variability model of IoT embodied agents; (ii) feedback evaluative machine learning; and (iii) reconfiguration of a group of agents in accordance with environmental context. The proposed approach advances the state of the art in that it facilitates the development of Agent-based IoT applications by explicitly capturing their complex and dynamic variabilities and supporting their self-configuration based on an context-aware and machine learning-based approach.
Tasks
Published	2018-12-14
URL	http://arxiv.org/abs/1812.06791v1
PDF	http://arxiv.org/pdf/1812.06791v1.pdf
PWC	https://paperswithcode.com/paper/an-iot-analytics-embodied-agent-model-based
Repo
Framework

An Exploration of Dropout with RNNs for Natural Language Inference


Title	An Exploration of Dropout with RNNs for Natural Language Inference
Authors	Amit Gajbhiye, Sardar Jaf, Noura Al Moubayed, A. Stephen McGough, Steven Bradley
Abstract	Dropout is a crucial regularization technique for the Recurrent Neural Network (RNN) models of Natural Language Inference (NLI). However, dropout has not been evaluated for the effectiveness at different layers and dropout rates in NLI models. In this paper, we propose a novel RNN model for NLI and empirically evaluate the effect of applying dropout at different layers in the model. We also investigate the impact of varying dropout rates at these layers. Our empirical evaluation on a large (Stanford Natural Language Inference (SNLI)) and a small (SciTail) dataset suggest that dropout at each feed-forward connection severely affects the model accuracy at increasing dropout rates. We also show that regularizing the embedding layer is efficient for SNLI whereas regularizing the recurrent layer improves the accuracy for SciTail. Our model achieved an accuracy 86.14% on the SNLI dataset and 77.05% on SciTail.
Tasks	Natural Language Inference
Published	2018-10-22
URL	http://arxiv.org/abs/1810.08606v1
PDF	http://arxiv.org/pdf/1810.08606v1.pdf
PWC	https://paperswithcode.com/paper/an-exploration-of-dropout-with-rnns-for
Repo
Framework

Application of Deep Learning on Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations


Title	Application of Deep Learning on Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations
Authors	Mei Lin, Vanya Jaitly, Iris Wang, Zhihong Hu, Lei Chen, Md. Amer Wahed, Zeyad Kanaan, Adan Rios, Andy N. D. Nguyen
Abstract	We explore how Deep Learning (DL) can be utilized to predict prognosis of acute myeloid leukemia (AML). Out of TCGA (The Cancer Genome Atlas) database, 94 AML cases are used in this study. Input data include age, 10 common cytogenetic and 23 most common mutation results; output is the prognosis (diagnosis to death, DTD). In our DL network, autoencoders are stacked to form a hierarchical DL model from which raw data are compressed and organized and high-level features are extracted. The network is written in R language and is designed to predict prognosis of AML for a given case (DTD of more than or less than 730 days). The DL network achieves an excellent accuracy of 83% in predicting prognosis. As a proof-of-concept study, our preliminary results demonstrate a practical application of DL in future practice of prognostic prediction using next-gen sequencing (NGS) data.
Tasks
Published	2018-10-30
URL	http://arxiv.org/abs/1810.13247v1
PDF	http://arxiv.org/pdf/1810.13247v1.pdf
PWC	https://paperswithcode.com/paper/application-of-deep-learning-on-predicting
Repo
Framework

Smoothed Analysis in Unsupervised Learning via Decoupling


Title	Smoothed Analysis in Unsupervised Learning via Decoupling
Authors	Aditya Bhaskara, Aidao Chen, Aidan Perreault, Aravindan Vijayaraghavan
Abstract	Smoothed analysis is a powerful paradigm in overcoming worst-case intractability in unsupervised learning and high-dimensional data analysis. While polynomial time smoothed analysis guarantees have been obtained for worst-case intractable problems like tensor decompositions and learning mixtures of Gaussians, such guarantees have been hard to obtain for several other important problems in unsupervised learning. A core technical challenge in analyzing algorithms is obtaining lower bounds on the least singular value for random matrix ensembles with dependent entries, that are given by low-degree polynomials of a few base underlying random variables. In this work, we address this challenge by obtaining high-confidence lower bounds on the least singular value of new classes of structured random matrix ensembles of the above kind. We then use these bounds to design algorithms with polynomial time smoothed analysis guarantees for the following three important problems in unsupervised learning: 1. Robust subspace recovery, when the fraction $\alpha$ of inliers in the d-dimensional subspace $T \subset \mathbb{R}^n$ is at least $\alpha > (d/n)^\ell$ for any constant integer $\ell>0$. This contrasts with the known worst-case intractability when $\alpha< d/n$, and the previous smoothed analysis result which needed $\alpha > d/n$ (Hardt and Moitra, 2013). 2. Learning overcomplete hidden markov models, where the size of the state space is any polynomial in the dimension of the observations. This gives the first polynomial time guarantees for learning overcomplete HMMs in a smoothed analysis model. 3. Higher order tensor decompositions, where we generalize the so-called FOOBI algorithm of Cardoso to find order-$\ell$ rank-one tensors in a subspace. This allows us to obtain polynomially robust decomposition algorithms for $2\ell$'th order tensors with rank $O(n^{\ell})$.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12361v2
PDF	http://arxiv.org/pdf/1811.12361v2.pdf
PWC	https://paperswithcode.com/paper/smoothed-analysis-in-unsupervised-learning
Repo
Framework

Barista - a Graphical Tool for Designing and Training Deep Neural Networks


Title	Barista - a Graphical Tool for Designing and Training Deep Neural Networks
Authors	Soeren Klemm, Aaron Scherzinger, Dominik Drees, Xiaoyi Jiang
Abstract	In recent years, the importance of deep learning has significantly increased in pattern recognition, computer vision, and artificial intelligence research, as well as in industry. However, despite the existence of multiple deep learning frameworks, there is a lack of comprehensible and easy-to-use high-level tools for the design, training, and testing of deep neural networks (DNNs). In this paper, we introduce Barista, an open-source graphical high-level interface for the Caffe deep learning framework. While Caffe is one of the most popular frameworks for training DNNs, editing prototext files in order to specify the net architecture and hyper parameters can become a cumbersome and error-prone task. Instead, Barista offers a fully graphical user interface with a graph-based net topology editor and provides an end-to-end training facility for DNNs, which allows researchers to focus on solving their problems without having to write code, edit text files, or manually parse logged data.
Tasks
Published	2018-02-13
URL	http://arxiv.org/abs/1802.04626v1
PDF	http://arxiv.org/pdf/1802.04626v1.pdf
PWC	https://paperswithcode.com/paper/barista-a-graphical-tool-for-designing-and
Repo
Framework

Automated Phenotyping of Epicuticular Waxes of Grapevine Berries Using Light Separation and Convolutional Neural Networks


Title	Automated Phenotyping of Epicuticular Waxes of Grapevine Berries Using Light Separation and Convolutional Neural Networks
Authors	Pierre Barré, Katja Herzog, Rebecca Höfle, Matthias B. Hullin, Reinhard Töpfer, Volker Steinhage
Abstract	In viticulture the epicuticular wax as the outer layer of the berry skin is known as trait which is correlated to resilience towards Botrytis bunch rot. Traditionally this trait is classified using the OIV descriptor 227 (berry bloom) in a time consuming way resulting in subjective and error-prone phenotypic data. In the present study an objective, fast and sensor-based approach was developed to monitor berry bloom. From the technical point-of-view, it is known that the measurement of different illumination components conveys important information about observed object surfaces. A Mobile Light-Separation-Lab is proposed in order to capture illumination-separated images of grapevine berries for phenotyping the distribution of epicuticular waxes (berry bloom). For image analysis, an efficient convolutional neural network approach is used to derive the uniformity and intactness of waxes on berries. Method validation over six grapevine cultivars shows accuracies up to $97.3$%. In addition, electrical impedance of the cuticle and its epicuticular waxes (described as an indicator for the thickness of berry skin and its permeability) was correlated to the detected proportion of waxes with $r=0.76$. This novel, fast and non-invasive phenotyping approach facilitates enlarged screenings within grapevine breeding material and genetic repositories regarding berry bloom characteristics and its impact on resilience towards Botrytis bunch rot.
Tasks
Published	2018-07-19
URL	http://arxiv.org/abs/1807.07343v3
PDF	http://arxiv.org/pdf/1807.07343v3.pdf
PWC	https://paperswithcode.com/paper/automated-phenotyping-of-epicuticular-waxes
Repo
Framework

Local Learning with Deep and Handcrafted Features for Facial Expression Recognition


Title	Local Learning with Deep and Handcrafted Features for Facial Expression Recognition
Authors	Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Marius Popescu
Abstract	We present an approach that combines automatic features learned by convolutional neural networks (CNN) and handcrafted features computed by the bag-of-visual-words (BOVW) model in order to achieve state-of-the-art results in facial expression recognition. To obtain automatic features, we experiment with multiple CNN architectures, pre-trained models and training procedures, e.g. Dense-Sparse-Dense. After fusing the two types of features, we employ a local learning framework to predict the class label for each test image. The local learning framework is based on three steps. First, a k-nearest neighbors model is applied in order to select the nearest training samples for an input test image. Second, a one-versus-all Support Vector Machines (SVM) classifier is trained on the selected training samples. Finally, the SVM classifier is used to predict the class label only for the test image it was trained for. Although we have used local learning in combination with handcrafted features in our previous work, to the best of our knowledge, local learning has never been employed in combination with deep features. The experiments on the 2013 Facial Expression Recognition (FER) Challenge data set, the FER+ data set and the AffectNet data set demonstrate that our approach achieves state-of-the-art results. With a top accuracy of 75.42% on FER 2013, 87.76% on the FER+, 59.58% on AffectNet 8-way classification and 63.31% on AffectNet 7-way classification, we surpass the state-of-the-art methods by more than 1% on all data sets.
Tasks	Facial Expression Recognition
Published	2018-04-29
URL	https://arxiv.org/abs/1804.10892v7
PDF	https://arxiv.org/pdf/1804.10892v7.pdf
PWC	https://paperswithcode.com/paper/local-learning-with-deep-and-handcrafted
Repo
Framework

Super Diffusion for Salient Object Detection


Title	Super Diffusion for Salient Object Detection
Authors	Peng Jiang, Zhiyi Pan, Nuno Vasconcelos, Baoquan Chen, Jingliang Peng
Abstract	One major branch of saliency object detection methods is diffusion-based which construct a graph model on a given image and diffuse seed saliency values to the whole graph by a diffusion matrix. While their performance is sensitive to specific feature spaces and scales used for the diffusion matrix definition, little work has been published to systematically promote the robustness and accuracy of salient object detection under the generic mechanism of diffusion. In this work, we firstly present a novel view of the working mechanism of the diffusion process based on mathematical analysis, which reveals that the diffusion process is actually computing the similarity of nodes with respect to the seeds based on diffusion maps. Following this analysis, we propose super diffusion, a novel inclusive learning-based framework for salient object detection, which makes the optimum and robust performance by integrating a large pool of feature spaces, scales and even features originally computed for non-diffusion-based salient object detection. A closed-form solution of the optimal parameters for the integration is determined through supervised learning. At the local level, we propose to promote each individual diffusion before the integration. Our mathematical analysis reveals the close relationship between saliency diffusion and spectral clustering. Based on this, we propose to re-synthesize each individual diffusion matrix from the most discriminative eigenvectors and the constant eigenvector (for saliency normalization). The proposed framework is implemented and experimented on prevalently used benchmark datasets, consistently leading to state-of-the-art performance.
Tasks	Object Detection, Salient Object Detection
Published	2018-11-22
URL	http://arxiv.org/abs/1811.09038v1
PDF	http://arxiv.org/pdf/1811.09038v1.pdf
PWC	https://paperswithcode.com/paper/super-diffusion-for-salient-object-detection
Repo
Framework

Exploring the Applications of Faster R-CNN and Single-Shot Multi-box Detection in a Smart Nursery Domain


Title	Exploring the Applications of Faster R-CNN and Single-Shot Multi-box Detection in a Smart Nursery Domain
Authors	Somnuk Phon-Amnuaisuk, Ken T. Murata, Praphan Pavarangkoon, Kazunori Yamamoto, Takamichi Mizuhara
Abstract	The ultimate goal of a baby detection task concerns detecting the presence of a baby and other objects in a sequence of 2D images, tracking them and understanding the semantic contents of the scene. Recent advances in deep learning and computer vision offer various powerful tools in general object detection and can be applied to a baby detection task. In this paper, the Faster Region-based Convolutional Neural Network and the Single-Shot Multi-Box Detection approaches are explored. They are the two state-of-the-art object detectors based on the region proposal tactic and the multi-box tactic. The presence of a baby in the scene obtained from these detectors, tested using different pre-trained models, are discussed. This study is important since the behaviors of these detectors in a baby detection task using different pre-trained models are still not well understood. This exploratory study reveals many useful insights into the applications of these object detectors in the smart nursery domain.
Tasks	Object Detection
Published	2018-08-27
URL	http://arxiv.org/abs/1808.08675v1
PDF	http://arxiv.org/pdf/1808.08675v1.pdf
PWC	https://paperswithcode.com/paper/exploring-the-applications-of-faster-r-cnn
Repo
Framework