July 28, 2019

3143 words 15 mins read

Paper Group ANR 356

On Scalable Inference with Stochastic Gradient Descent. Single-Shot Clothing Category Recognition in Free-Configurations with Application to Autonomous Clothes Sorting. Preselection via Classification: A Case Study on Evolutionary Multiobjective Optimization. A Generally Applicable, Highly Scalable Measurement Computation and Optimization Approach …

On Scalable Inference with Stochastic Gradient Descent


Title	On Scalable Inference with Stochastic Gradient Descent
Authors	Yixin Fang, Jinfeng Xu, Lei Yang
Abstract	In many applications involving large dataset or online updating, stochastic gradient descent (SGD) provides a scalable way to compute parameter estimates and has gained increasing popularity due to its numerical convenience and memory efficiency. While the asymptotic properties of SGD-based estimators have been established decades ago, statistical inference such as interval estimation remains much unexplored. The traditional resampling method such as the bootstrap is not computationally feasible since it requires to repeatedly draw independent samples from the entire dataset. The plug-in method is not applicable when there are no explicit formulas for the covariance matrix of the estimator. In this paper, we propose a scalable inferential procedure for stochastic gradient descent, which, upon the arrival of each observation, updates the SGD estimate as well as a large number of randomly perturbed SGD estimates. The proposed method is easy to implement in practice. We establish its theoretical properties for a general class of models that includes generalized linear models and quantile regression models as special cases. The finite-sample performance and numerical utility is evaluated by simulation studies and two real data applications.
Tasks
Published	2017-07-01
URL	http://arxiv.org/abs/1707.00192v1
PDF	http://arxiv.org/pdf/1707.00192v1.pdf
PWC	https://paperswithcode.com/paper/on-scalable-inference-with-stochastic
Repo
Framework

Single-Shot Clothing Category Recognition in Free-Configurations with Application to Autonomous Clothes Sorting


Title	Single-Shot Clothing Category Recognition in Free-Configurations with Application to Autonomous Clothes Sorting
Authors	Li Sun, Gerardo Aragon-Camarasa, Simon Rogers, Rustam Stolkin, J. Paul Siebert
Abstract	This paper proposes a single-shot approach for recognising clothing categories from 2.5D features. We propose two visual features, BSP (B-Spline Patch) and TSD (Topology Spatial Distances) for this task. The local BSP features are encoded by LLC (Locality-constrained Linear Coding) and fused with three different global features. Our visual feature is robust to deformable shapes and our approach is able to recognise the category of unknown clothing in unconstrained and random configurations. We integrated the category recognition pipeline with a stereo vision system, clothing instance detection, and dual-arm manipulators to achieve an autonomous sorting system. To verify the performance of our proposed method, we build a high-resolution RGBD clothing dataset of 50 clothing items of 5 categories sampled in random configurations (a total of 2,100 clothing samples). Experimental results show that our approach is able to reach 83.2% accuracy while classifying clothing items which were previously unseen during training. This advances beyond the previous state-of-the-art by 36.2%. Finally, we evaluate the proposed approach in an autonomous robot sorting system, in which the robot recognises a clothing item from an unconstrained pile, grasps it, and sorts it into a box according to its category. Our proposed sorting system achieves reasonable sorting success rates with single-shot perception.
Tasks
Published	2017-07-22
URL	http://arxiv.org/abs/1707.07157v1
PDF	http://arxiv.org/pdf/1707.07157v1.pdf
PWC	https://paperswithcode.com/paper/single-shot-clothing-category-recognition-in
Repo
Framework

Preselection via Classification: A Case Study on Evolutionary Multiobjective Optimization


Title	Preselection via Classification: A Case Study on Evolutionary Multiobjective Optimization
Authors	Jinyuan Zhang, Aimin Zhou, Ke Tang, Guixu Zhang
Abstract	In evolutionary algorithms, a preselection operator aims to select the promising offspring solutions from a candidate offspring set. It is usually based on the estimated or real objective values of the candidate offspring solutions. In a sense, the preselection can be treated as a classification procedure, which classifies the candidate offspring solutions into promising ones and unpromising ones. Following this idea, we propose a classification based preselection (CPS) strategy for evolutionary multiobjective optimization. When applying classification based preselection, an evolutionary algorithm maintains two external populations (training data set) that consist of some selected good and bad solutions found so far; then it trains a classifier based on the training data set in each generation. Finally it uses the classifier to filter the unpromising candidate offspring solutions and choose a promising one from the generated candidate offspring set for each parent solution. In such cases, it is not necessary to estimate or evaluate the objective values of the candidate offspring solutions. The classification based preselection is applied to three state-of-the-art multiobjective evolutionary algorithms (MOEAs) and is empirically studied on two sets of test instances. The experimental results suggest that classification based preselection can successfully improve the performance of these MOEAs.
Tasks	Multiobjective Optimization
Published	2017-08-03
URL	http://arxiv.org/abs/1708.01146v1
PDF	http://arxiv.org/pdf/1708.01146v1.pdf
PWC	https://paperswithcode.com/paper/preselection-via-classification-a-case-study
Repo
Framework

A Generally Applicable, Highly Scalable Measurement Computation and Optimization Approach to Sequential Model-Based Diagnosis


Title	A Generally Applicable, Highly Scalable Measurement Computation and Optimization Approach to Sequential Model-Based Diagnosis
Authors	Patrick Rodler, Wolfgang Schmid, Konstantin Schekotihin
Abstract	Model-Based Diagnosis deals with the identification of the real cause of a system’s malfunction based on a formal system model and observations of the system behavior. When a malfunction is detected, there is usually not enough information available to pinpoint the real cause and one needs to discriminate between multiple fault hypotheses (called diagnoses). To this end, Sequential Diagnosis approaches ask an oracle for additional system measurements. This work presents strategies for (optimal) measurement selection in model-based sequential diagnosis. In particular, assuming a set of leading diagnoses being given, we show how queries (sets of measurements) can be computed and optimized along two dimensions: expected number of queries and cost per query. By means of a suitable decoupling of two optimizations and a clever search space reduction the computations are done without any inference engine calls. For the full search space, we give a method requiring only a polynomial number of inferences and show how query properties can be guaranteed which existing methods do not provide. Evaluation results using real-world problems indicate that the new method computes (virtually) optimal queries instantly independently of the size and complexity of the considered diagnosis problems and outperforms equally general methods not exploiting the proposed theory by orders of magnitude.
Tasks	Sequential Diagnosis
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05508v1
PDF	http://arxiv.org/pdf/1711.05508v1.pdf
PWC	https://paperswithcode.com/paper/a-generally-applicable-highly-scalable
Repo
Framework

The CLaC Discourse Parser at CoNLL-2015


Title	The CLaC Discourse Parser at CoNLL-2015
Authors	Majid Laali, Elnaz Davoodi, Leila Kosseim
Abstract	This paper describes our submission (kosseim15) to the CoNLL-2015 shared task on shallow discourse parsing. We used the UIMA framework to develop our parser and used ClearTK to add machine learning functionality to the UIMA framework. Overall, our parser achieves a result of 17.3 F1 on the identification of discourse relations on the blind CoNLL-2015 test set, ranking in sixth place.
Tasks
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05857v1
PDF	http://arxiv.org/pdf/1708.05857v1.pdf
PWC	https://paperswithcode.com/paper/the-clac-discourse-parser-at-conll-2015
Repo
Framework

A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening


Title	A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening
Authors	Qiangqiang Yuan, Yancong Wei, Xiangchao Meng, Huanfeng Shen, Liangpei Zhang
Abstract	Pan-sharpening is a fundamental and significant task in the field of remote sensing imagery processing, in which high-resolution spatial details from panchromatic images are employed to enhance the spatial resolution of multi-spectral (MS) images. As the transformation from low spatial resolution MS image to high-resolution MS image is complex and highly non-linear, inspired by the powerful representation for non-linear relationships of deep neural networks, we introduce multi-scale feature extraction and residual learning into the basic convolutional neural network (CNN) architecture and propose the multi-scale and multi-depth convolutional neural network (MSDCNN) for the pan-sharpening of remote sensing imagery. Both the quantitative assessment results and the visual assessment confirm that the proposed network yields high-resolution MS images that are superior to the images produced by the compared state-of-the-art methods.
Tasks
Published	2017-12-28
URL	http://arxiv.org/abs/1712.09809v1
PDF	http://arxiv.org/pdf/1712.09809v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-scale-and-multi-depth-convolutional
Repo
Framework

An Accelerated Analog Neuromorphic Hardware System Emulating NMDA- and Calcium-Based Non-Linear Dendrites


Title	An Accelerated Analog Neuromorphic Hardware System Emulating NMDA- and Calcium-Based Non-Linear Dendrites
Authors	Johannes Schemmel, Laura Kriener, Paul Müller, Karlheinz Meier
Abstract	This paper presents an extension of the BrainScaleS accelerated analog neuromorphic hardware model. The scalable neuromorphic architecture is extended by the support for multi-compartment models and non-linear dendrites. These features are part of a \SI{65}{\nano\meter} prototype ASIC. It allows to emulate different spike types observed in cortical pyramidal neurons: NMDA plateau potentials, calcium and sodium spikes. By replicating some of the structures of these cells, they can be configured to perform coincidence detection within a single neuron. Built-in plasticity mechanisms can modify not only the synaptic weights, but also the dendritic synaptic composition to efficiently train large multi-compartment neurons. Transistor-level simulations demonstrate the functionality of the analog implementation and illustrate analogies to biological measurements.
Tasks
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07286v1
PDF	http://arxiv.org/pdf/1703.07286v1.pdf
PWC	https://paperswithcode.com/paper/an-accelerated-analog-neuromorphic-hardware
Repo
Framework

Agent-based computing from multi-agent systems to agent-based Models: a visual survey


Title	Agent-based computing from multi-agent systems to agent-based Models: a visual survey
Authors	Muaz A. Niazi, Amir Hussain
Abstract	Agent-Based Computing is a diverse research domain concerned with the building of intelligent software based on the concept of “agents”. In this paper, we use Scientometric analysis to analyze all sub-domains of agent-based computing. Our data consists of 1,064 journal articles indexed in the ISI web of knowledge published during a twenty year period: 1990-2010. These were retrieved using a topic search with various keywords commonly used in sub-domains of agent-based computing. In our proposed approach, we have employed a combination of two applications for analysis, namely Network Workbench and CiteSpace - wherein Network Workbench allowed for the analysis of complex network aspects of the domain, detailed visualization-based analysis of the bibliographic data was performed using CiteSpace. Our results include the identification of the largest cluster based on keywords, the timeline of publication of index terms, the core journals and key subject categories. We also identify the core authors, top countries of origin of the manuscripts along with core research institutes. Finally, our results have interestingly revealed the strong presence of agent-based computing in a number of non-computing related scientific domains including Life Sciences, Ecological Sciences and Social Sciences.
Tasks
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05872v1
PDF	http://arxiv.org/pdf/1708.05872v1.pdf
PWC	https://paperswithcode.com/paper/agent-based-computing-from-multi-agent
Repo
Framework

Weakly-supervised DCNN for RGB-D Object Recognition in Real-World Applications Which Lack Large-scale Annotated Training Data


Title	Weakly-supervised DCNN for RGB-D Object Recognition in Real-World Applications Which Lack Large-scale Annotated Training Data
Authors	Li Sun, Cheng Zhao, Rustam Stolkin
Abstract	This paper addresses the problem of RGBD object recognition in real-world applications, where large amounts of annotated training data are typically unavailable. To overcome this problem, we propose a novel, weakly-supervised learning architecture (DCNN-GPC) which combines parametric models (a pair of Deep Convolutional Neural Networks (DCNN) for RGB and D modalities) with non-parametric models (Gaussian Process Classification). Our system is initially trained using a small amount of labeled data, and then automatically prop- agates labels to large-scale unlabeled data. We first run 3D- based objectness detection on RGBD videos to acquire many unlabeled object proposals, and then employ DCNN-GPC to label them. As a result, our multi-modal DCNN can be trained end-to-end using only a small amount of human annotation. Finally, our 3D-based objectness detection and multi-modal DCNN are integrated into a real-time detection and recognition pipeline. In our approach, bounding-box annotations are not required and boundary-aware detection is achieved. We also propose a novel way to pretrain a DCNN for the depth modality, by training on virtual depth images projected from CAD models. We pretrain our multi-modal DCNN on public 3D datasets, achieving performance comparable to state-of-the-art methods on Washington RGBS Dataset. We then finetune the network by further training on a small amount of annotated data from our novel dataset of industrial objects (nuclear waste simulants). Our weakly supervised approach has demonstrated to be highly effective in solving a novel RGBD object recognition application which lacks of human annotations.
Tasks	Object Recognition
Published	2017-03-19
URL	http://arxiv.org/abs/1703.06370v1
PDF	http://arxiv.org/pdf/1703.06370v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-dcnn-for-rgb-d-object
Repo
Framework

Synthesising Wider Field Images from Narrow-Field Retinal Video Acquired Using a Low-Cost Direct Ophthalmoscope (Arclight) Attached to a Smartphone


Title	Synthesising Wider Field Images from Narrow-Field Retinal Video Acquired Using a Low-Cost Direct Ophthalmoscope (Arclight) Attached to a Smartphone
Authors	Keylor Daniel Chaves Viquez, Ognjen Arandjelovic, Andrew Blaikie, In Ae Hwang
Abstract	Access to low cost retinal imaging devices in low and middle income countries is limited, compromising progress in preventing needless blindness. The Arclight is a recently developed low-cost solar powered direct ophthalmoscope which can be attached to the camera of a smartphone to acquire retinal images and video. However, the acquired data is inherently limited by the optics of direct ophthalmoscopy, resulting in a narrow field of view with associated corneal reflections, limiting its usefulness. In this work we describe the first fully automatic method utilizing videos acquired using the Arclight attached to a mobile phone camera to create wider view, higher quality still images comparable with images obtained using much more expensive and bulky dedicated traditional retinal cameras.
Tasks
Published	2017-08-26
URL	http://arxiv.org/abs/1708.07977v1
PDF	http://arxiv.org/pdf/1708.07977v1.pdf
PWC	https://paperswithcode.com/paper/synthesising-wider-field-images-from-narrow
Repo
Framework

What Drives the International Development Agenda? An NLP Analysis of the United Nations General Debate 1970-2016


Title	What Drives the International Development Agenda? An NLP Analysis of the United Nations General Debate 1970-2016
Authors	Alexander Baturo, Niheer Dasandi, Slava J. Mikhaylov
Abstract	There is surprisingly little known about agenda setting for international development in the United Nations (UN) despite it having a significant influence on the process and outcomes of development efforts. This paper addresses this shortcoming using a novel approach that applies natural language processing techniques to countries’ annual statements in the UN General Debate. Every year UN member states deliver statements during the General Debate on their governments’ perspective on major issues in world politics. These speeches provide invaluable information on state preferences on a wide range of issues, including international development, but have largely been overlooked in the study of global politics. This paper identifies the main international development topics that states raise in these speeches between 1970 and 2016, and examine the country-specific drivers of international development rhetoric.
Tasks
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05873v1
PDF	http://arxiv.org/pdf/1708.05873v1.pdf
PWC	https://paperswithcode.com/paper/what-drives-the-international-development
Repo
Framework

Variance Regularizing Adversarial Learning


Title	Variance Regularizing Adversarial Learning
Authors	Karan Grewal, R Devon Hjelm, Yoshua Bengio
Abstract	We introduce a novel approach for training adversarial models by replacing the discriminator score with a bi-modal Gaussian distribution over the real/fake indicator variables. In order to do this, we train the Gaussian classifier to match the target bi-modal distribution implicitly through meta-adversarial training. We hypothesize that this approach ensures a non-zero gradient to the generator, even in the limit of a perfect classifier. We test our method against standard benchmark image datasets as well as show the classifier output distribution is smooth and has overlap between the real and fake modes.
Tasks
Published	2017-07-02
URL	http://arxiv.org/abs/1707.00309v2
PDF	http://arxiv.org/pdf/1707.00309v2.pdf
PWC	https://paperswithcode.com/paper/variance-regularizing-adversarial-learning
Repo
Framework

Recruitment Market Trend Analysis with Sequential Latent Variable Models


Title	Recruitment Market Trend Analysis with Sequential Latent Variable Models
Authors	Chen Zhu, Hengshu Zhu, Hui Xiong, Pengliang Ding, Fang Xie
Abstract	Recruitment market analysis provides valuable understanding of industry-specific economic growth and plays an important role for both employers and job seekers. With the rapid development of online recruitment services, massive recruitment data have been accumulated and enable a new paradigm for recruitment market analysis. However, traditional methods for recruitment market analysis largely rely on the knowledge of domain experts and classic statistical models, which are usually too general to model large-scale dynamic recruitment data, and have difficulties to capture the fine-grained market trends. To this end, in this paper, we propose a new research paradigm for recruitment market analysis by leveraging unsupervised learning techniques for automatically discovering recruitment market trends based on large-scale recruitment data. Specifically, we develop a novel sequential latent variable model, named MTLVM, which is designed for capturing the sequential dependencies of corporate recruitment states and is able to automatically learn the latent recruitment topics within a Bayesian generative framework. In particular, to capture the variability of recruitment topics over time, we design hierarchical dirichlet processes for MTLVM. These processes allow to dynamically generate the evolving recruitment topics. Finally, we implement a prototype system to empirically evaluate our approach based on real-world recruitment data in China. Indeed, by visualizing the results from MTLVM, we can successfully reveal many interesting findings, such as the popularity of LBS related jobs reached the peak in the 2nd half of 2014, and decreased in 2015.
Tasks	Latent Variable Models
Published	2017-12-08
URL	http://arxiv.org/abs/1712.02975v1
PDF	http://arxiv.org/pdf/1712.02975v1.pdf
PWC	https://paperswithcode.com/paper/recruitment-market-trend-analysis-with
Repo
Framework

Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation


Title	Teaching UAVs to Race: End-to-End Regression of Agile Controls in Simulation
Authors	Matthias Müller, Vincent Casser, Neil Smith, Dominik L. Michels, Bernard Ghanem
Abstract	Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years. However, teaching UAVs to fly in challenging environments remains an unsolved problem, mainly due to the lack of training data. In this paper, we train a deep neural network to predict UAV controls from raw image data for the task of autonomous UAV racing in a photo-realistic simulation. Training is done through imitation learning with data augmentation to allow for the correction of navigation mistakes. Extensive experiments demonstrate that our trained network (when sufficient data augmentation is used) outperforms state-of-the-art methods and flies more consistently than many human pilots. Additionally, we show that our optimized network architecture can run in real-time on embedded hardware, allowing for efficient on-board processing critical for real-world deployment. From a broader perspective, our results underline the importance of extensive data augmentation techniques to improve robustness in end-to-end learning setups.
Tasks	Data Augmentation, Imitation Learning
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05884v4
PDF	http://arxiv.org/pdf/1708.05884v4.pdf
PWC	https://paperswithcode.com/paper/teaching-uavs-to-race-end-to-end-regression
Repo
Framework

Calibration of Machine Learning Classifiers for Probability of Default Modelling


Title	Calibration of Machine Learning Classifiers for Probability of Default Modelling
Authors	Pedro G. Fonseca, Hugo D. Lopes
Abstract	Binary classification is highly used in credit scoring in the estimation of probability of default. The validation of such predictive models is based both on rank ability, and also on calibration (i.e. how accurately the probabilities output by the model map to the observed probabilities). In this study we cover the current best practices regarding calibration for binary classification, and explore how different approaches yield different results on real world credit scoring data. The limitations of evaluating credit scoring models using only rank ability metrics are explored. A benchmark is run on 18 real world datasets, and results compared. The calibration techniques used are Platt Scaling and Isotonic Regression. Also, different machine learning models are used: Logistic Regression, Random Forest Classifiers, and Gradient Boosting Classifiers. Results show that when the dataset is treated as a time series, the use of re-calibration with Isotonic Regression is able to improve the long term calibration better than the alternative methods. Using re-calibration, the non-parametric models are able to outperform the Logistic Regression on Brier Score Loss.
Tasks	Calibration, Time Series
Published	2017-10-24
URL	http://arxiv.org/abs/1710.08901v1
PDF	http://arxiv.org/pdf/1710.08901v1.pdf
PWC	https://paperswithcode.com/paper/calibration-of-machine-learning-classifiers
Repo
Framework