April 1, 2020

2805 words 14 mins read

Paper Group ANR 409

Paper Group ANR 409

Interactive Constrained MAP-Elites Analysis and Evaluation of the Expressiveness of the Feature Dimensions. Machine Translation System Selection from Bandit Feedback. Monte Carlo Tree Search for Generating Interactive Data Analysis Interfaces. Experimenting with Convolutional Neural Network Architectures for the automatic characterization of Solita …

Interactive Constrained MAP-Elites Analysis and Evaluation of the Expressiveness of the Feature Dimensions

Title Interactive Constrained MAP-Elites Analysis and Evaluation of the Expressiveness of the Feature Dimensions
Authors Alberto Alvarez, Steve Dahlskog, Jose Font, Julian Togelius
Abstract We propose the Interactive Constrained MAP-Elites, a quality-diversity solution for game content generation, implemented as a new feature of the Evolutionary Dungeon Designer: a mixed-initiative co-creativity tool for designing dungeons. The feature uses the MAP-Elites algorithm, an illumination algorithm that segregates the population among several cells depending on their scores with respect to different behavioral dimensions. Users can flexibly and dynamically alternate between these dimensions anytime, thus guiding the evolutionary process in an intuitive way, and then incorporate suggestions produced by the algorithm in their room designs. At the same time, any modifications performed by the human user will feed back into MAP-Elites, closing a circular workflow of constant mutual inspiration. This paper presents the algorithm followed by an in-depth analysis of its behaviour, with the aims of evaluating the expressive range of all possible dimension combinations in several scenarios, as well as discussing their influence in the fitness landscape and in the overall performance of the mixed-initiative procedural content generation.
Published 2020-03-06
URL https://arxiv.org/abs/2003.03377v1
PDF https://arxiv.org/pdf/2003.03377v1.pdf
PWC https://paperswithcode.com/paper/interactive-constrained-map-elites-analysis

Machine Translation System Selection from Bandit Feedback

Title Machine Translation System Selection from Bandit Feedback
Authors Jason Naradowsky, Xuan Zhang, Kevin Duh
Abstract Adapting machine translation systems in the real world is a difficult problem. In contrast to offline training, users cannot provide the type of fine-grained feedback typically used for improving the system. Moreover, users have different translation needs, and even a single user’s needs may change over time. In this work we take a different approach, treating the problem of adapting as one of selection. Instead of adapting a single system, we train many translation systems using different architectures and data partitions. Using bandit learning techniques on simulated user feedback, we learn a policy to choose which system to use for a particular translation task. We show that our approach can (1) quickly adapt to address domain changes in translation tasks, (2) outperform the single best system in mixed-domain translation tasks, and (3) make effective instance-specific decisions when using contextual bandit strategies.
Tasks Machine Translation
Published 2020-02-22
URL https://arxiv.org/abs/2002.09646v1
PDF https://arxiv.org/pdf/2002.09646v1.pdf
PWC https://paperswithcode.com/paper/machine-translation-system-selection-from

Monte Carlo Tree Search for Generating Interactive Data Analysis Interfaces

Title Monte Carlo Tree Search for Generating Interactive Data Analysis Interfaces
Authors Yiru Chen, Eugene Wu
Abstract Interactive tools like user interfaces help democratize data access for end-users by hiding underlying programming details and exposing the necessary widget interface to users. Since customized interfaces are costly to build, automated interface generation is desirable. SQL is the dominant way to analyze data and there already exists logs to analyze data. Previous work proposed a syntactic approach to analyze structural changes in SQL query logs and automatically generates a set of widgets to express the changes. However, they do not consider layout usability and the sequential order of queries in the log. We propose to adopt Monte Carlo Tree Search(MCTS) to search for the optimal interface that accounts for hierarchical layout as well as the usability in terms of how easy to express the query log.
Published 2020-01-07
URL https://arxiv.org/abs/2001.01902v2
PDF https://arxiv.org/pdf/2001.01902v2.pdf
PWC https://paperswithcode.com/paper/monte-carlo-tree-search-for-generating

Experimenting with Convolutional Neural Network Architectures for the automatic characterization of Solitary Pulmonary Nodules’ malignancy rating

Title Experimenting with Convolutional Neural Network Architectures for the automatic characterization of Solitary Pulmonary Nodules’ malignancy rating
Authors Ioannis D. Apostolopoulos
Abstract Lung Cancer is the most common cause of cancer-related death worldwide. Early and automatic diagnosis of Solitary Pulmonary Nodules (SPN) in Computer Tomography (CT) chest scans can provide early treatment as well as doctor liberation from time-consuming procedures. Deep Learning has been proven as a popular and influential method in many medical imaging diagnosis areas. In this study, we consider the problem of diagnostic classification between benign and malignant lung nodules in CT images derived from a PET/CT scanner. More specifically, we intend to develop experimental Convolutional Neural Network (CNN) architectures and conduct experiments, by tuning their parameters, to investigate their behavior, and to define the optimal setup for the accurate classification. For the experiments, we utilize PET/CT images obtained from the Laboratory of Nuclear Medicine of the University of Patras, and the publically available database called Lung Image Database Consortium Image Collection (LIDC-IDRI). Furthermore, we apply simple data augmentation to generate new instances and to inspect the performance of the developed networks. Classification accuracy of 91% and 93% on the PET/CT dataset and on a selection of nodule images form the LIDC-IDRI dataset, is achieved accordingly. The results demonstrate that CNNs are a trustworth method for nodule classification. Also, the experiment confirms that data augmentation enhances the robustness of the CNNs.
Tasks Data Augmentation
Published 2020-03-15
URL https://arxiv.org/abs/2003.06801v1
PDF https://arxiv.org/pdf/2003.06801v1.pdf
PWC https://paperswithcode.com/paper/experimenting-with-convolutional-neural

Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule

Title Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule
Authors Nikhil Iyer, V Thejas, Nipun Kwatra, Ramachandran Ramjee, Muthian Sivathanu
Abstract While the generalization properties of neural networks are not yet well understood, several papers argue that wide minima generalize better than narrow minima. In this paper, through detailed experiments that not only corroborate the generalization properties of wide minima, we also provide empirical evidence for a new hypothesis that the density of wide minima is likely lower than the density of narrow minima. Further, motivated by this hypothesis, we design a novel explore-exploit learning rate schedule. On a variety of image and natural language datasets, compared to their original hand-tuned learning rate baselines, we show that our explore-exploit schedule can result in either up to 0.5% higher absolute accuracy using the original training budget or up to 44% reduced training time while achieving the original reported accuracy.
Published 2020-03-09
URL https://arxiv.org/abs/2003.03977v1
PDF https://arxiv.org/pdf/2003.03977v1.pdf
PWC https://paperswithcode.com/paper/wide-minima-density-hypothesis-and-the

AQPDBJUT Dataset: Picture-Based PM Monitoring in the Campus of BJUT

Title AQPDBJUT Dataset: Picture-Based PM Monitoring in the Campus of BJUT
Authors Yonghui Zhang, Ke Gu
Abstract Ensuring the students in good physical levels is imperative for their future health. In recent years, the continually growing concentration of Particulate Matter (PM) has done increasingly serious harm to student health. Hence, it is highly required to prevent and control PM concentrations in the campus. As the source of PM prevention and control, developing a good model for PM monitoring is extremely urgent and has posed a big challenge. It has been found in prior works that photobased methods are available for PM monitoring. To verify the effectiveness of existing PM monitoring methods in the campus, we establish a new dataset which includes 1,500 photos collected in the Beijing University of Technology. Experiments show that stated-of-the-art methods are far from ideal for PM monitoring in the campus.
Published 2020-03-19
URL https://arxiv.org/abs/2003.08609v2
PDF https://arxiv.org/pdf/2003.08609v2.pdf
PWC https://paperswithcode.com/paper/aqpdbjut-dataset-picture-based-pm25

Inceptive Event Time-Surfaces for Object Classification Using Neuromorphic Cameras

Title Inceptive Event Time-Surfaces for Object Classification Using Neuromorphic Cameras
Authors R Wes Baldwin, Mohammed Almatrafi, Jason R Kaufman, Vijayan Asari, Keigo Hirakawa
Abstract This paper presents a novel fusion of low-level approaches for dimensionality reduction into an effective approach for high-level objects in neuromorphic camera data called Inceptive Event Time-Surfaces (IETS). IETSs overcome several limitations of conventional time-surfaces by increasing robustness to noise, promoting spatial consistency, and improving the temporal localization of (moving) edges. Combining IETS with transfer learning improves state-of-the-art performance on the challenging problem of object classification utilizing event camera data.
Tasks Dimensionality Reduction, Object Classification, Temporal Localization, Transfer Learning
Published 2020-02-26
URL https://arxiv.org/abs/2002.11656v1
PDF https://arxiv.org/pdf/2002.11656v1.pdf
PWC https://paperswithcode.com/paper/inceptive-event-time-surfaces-for-object

Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences

Title Joint Visual-Temporal Embedding for Unsupervised Learning of Actions in Untrimmed Sequences
Authors Rosaura G. VidalMata, Walter J. Scheirer, Hilde Kuehne
Abstract Understanding the structure of complex activities in videos is one of the many challenges faced by action recognition methods. To overcome this challenge, not only do methods need a solid knowledge of the visual structure of underlying features but also a good interpretation of how they could change over time. Consequently, action segmentation tasks must take into account not only the visual cues from individual frames, but their characteristics as a temporal sequence of features. This work presents our findings on the impact of incorporating both visual and temporal learning on an unsupervised action segmentation pipeline. We introduce a novel approach to extract relevant visual and temporal features from untrimmed sequences for the temporal localization of sub-activities within complex actions without any labeling information. Through extensive experimentation on two benchmark datasets – Breakfast Actions, and YouTube Instructions – we show that the proposed approach is able to provide a meaningful visual and temporal embedding from the visual cues from contiguous video frames and that it indeed helps in temporal segmentation.
Tasks action segmentation, Temporal Localization
Published 2020-01-29
URL https://arxiv.org/abs/2001.11122v2
PDF https://arxiv.org/pdf/2001.11122v2.pdf
PWC https://paperswithcode.com/paper/joint-visual-temporal-embedding-for

Towards Physically-consistent, Data-driven Models of Convection

Title Towards Physically-consistent, Data-driven Models of Convection
Authors Tom Beucler, Michael Pritchard, Pierre Gentine, Stephan Rasp
Abstract Data-driven algorithms, in particular neural networks, can emulate the effect of sub-grid scale processes in coarse-resolution climate models if trained on high-resolution climate simulations. However, they may violate key physical constraints and lack the ability to generalize outside of their training set. Here, we show that physical constraints can be enforced in neural networks, either approximately by adapting the loss function or to machine precision by adapting the architecture. As these physical constraints are insufficient to guarantee generalizability, we additionally propose a framework to find physical normalizations that can be applied to the training and validation data to improve the ability of neural networks to generalize to unseen climates.
Published 2020-02-20
URL https://arxiv.org/abs/2002.08525v1
PDF https://arxiv.org/pdf/2002.08525v1.pdf
PWC https://paperswithcode.com/paper/towards-physically-consistent-data-driven

End-to-End Deep Diagnosis of X-ray Images

Title End-to-End Deep Diagnosis of X-ray Images
Authors Kudaibergen Urinbayev, Yerassyl Orazbek, Yernur Nurambek, Almas Mirzakhmetov, Huseyin Atakan Varol
Abstract In this work, we present an end-to-end deep learning framework for X-ray image diagnosis. As the first step, our system determines whether a submitted image is an X-ray or not. After it classifies the type of the X-ray, it runs the dedicated abnormality classification network. In this work, we only focus on the chest X-rays for abnormality classification. However, the system can be extended to other X-ray types easily. Our deep learning classifiers are based on DenseNet-121 architecture. The test set accuracy obtained for ‘X-ray or Not’, ‘X-ray Type Classification’, and ‘Chest Abnormality Classification’ tasks are 0.987, 0.976, and 0.947, respectively, resulting into an end-to-end accuracy of 0.91. For achieving better results than the state-of-the-art in the ‘Chest Abnormality Classification’, we utilize the new RAdam optimizer. We also use Gradient-weighted Class Activation Mapping for visual explanation of the results. Our results show the feasibility of a generalized online projectional radiography diagnosis system.
Published 2020-03-19
URL https://arxiv.org/abs/2003.08605v1
PDF https://arxiv.org/pdf/2003.08605v1.pdf
PWC https://paperswithcode.com/paper/end-to-end-deep-diagnosis-of-x-ray-images

A Rule-Based Model for Victim Prediction

Title A Rule-Based Model for Victim Prediction
Authors Murat Ozer, Nelly Elsayed, Said Varlioglu, Chengcheng Li
Abstract In this paper, we proposed a novel automated model, called Vulnerability Index for Population at Risk (VIPAR) scores, to identify rare populations for their future shooting victimizations. Likewise, the focused deterrence approach identifies vulnerable individuals and offers certain types of treatments (e.g., outreach services) to prevent violence in communities. The proposed rule-based engine model is the first AI-based model for victim prediction. This paper aims to compare the list of focused deterrence strategy with the VIPAR score list regarding their predictive power for the future shooting victimizations. Drawing on the criminological studies, the model uses age, past criminal history, and peer influence as the main predictors of future violence. Social network analysis is employed to measure the influence of peers on the outcome variable. The model also uses logistic regression analysis to verify the variable selections. Our empirical results show that VIPAR scores predict 25.8% of future shooting victims and 32.2% of future shooting suspects, whereas focused deterrence list predicts 13% of future shooting victims and 9.4% of future shooting suspects. The model outperforms the intelligence list of focused deterrence policies in predicting the future fatal and non-fatal shootings. Furthermore, we discuss the concerns about the presumption of innocence right.
Published 2020-01-06
URL https://arxiv.org/abs/2001.01391v2
PDF https://arxiv.org/pdf/2001.01391v2.pdf
PWC https://paperswithcode.com/paper/a-rule-based-model-for-victim-prediction

Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion

Title Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion
Authors Cyprien Ruffino, Romain Hérault, Eric Laloy, Gilles Gasso
Abstract Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. Several works have extended GANs to image inpainting by conditioning the generation with parts of the image to be reconstructed. Despite their success, these methods have limitations in settings where only a small subset of the image pixels is known beforehand. In this paper we investigate the effectiveness of conditioning GANs when very few pixel values are provided. We propose a modelling framework which results in adding an explicit cost term to the GAN objective function to enforce pixel-wise conditioning. We investigate the influence of this regularization term on the quality of the generated images and the fulfillment of the given pixel constraints. Using the recent PacGAN technique, we ensure that we keep diversity in the generated samples. Conducted experiments on FashionMNIST show that the regularization term effectively controls the trade-off between quality of the generated images and the conditioning. Experimental evaluation on the CIFAR-10 and CelebA datasets evidences that our method achieves accurate results both visually and quantitatively in term of Fr'echet Inception Distance, while still enforcing the pixel conditioning. We also evaluate our method on a texture image generation task using fully-convolutional networks. As a final contribution, we apply the method to a classical geological simulation application.
Tasks Image Generation, Image Inpainting
Published 2020-02-04
URL https://arxiv.org/abs/2002.01281v1
PDF https://arxiv.org/pdf/2002.01281v1.pdf
PWC https://paperswithcode.com/paper/pixel-wise-conditioned-generative-adversarial

MIME: Mutual Information Minimisation Exploration

Title MIME: Mutual Information Minimisation Exploration
Authors Haitao Xu, Brendan McCane, Lech Szymanski, Craig Atkinson
Abstract We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solution that we call Mutual Information Minimising Exploration (MIME) where an agent learns a latent representation of the environment without trying to predict the future states. We show that our agent performs significantly better over sharp transition boundaries while matching the performance of surprisal driven agents elsewhere. In particular, we show state-of-the-art performance on difficult learning games such as Gravitar, Montezuma’s Revenge and Doom.
Tasks Montezuma’s Revenge
Published 2020-01-16
URL https://arxiv.org/abs/2001.05636v1
PDF https://arxiv.org/pdf/2001.05636v1.pdf
PWC https://paperswithcode.com/paper/mime-mutual-information-minimisation

Verifying Deep Learning-based Decisions for Facial Expression Recognition

Title Verifying Deep Learning-based Decisions for Facial Expression Recognition
Authors Ines Rieger, Rene Kollmann, Bettina Finzel, Dominik Seuss, Ute Schmid
Abstract Neural networks with high performance can still be biased towards non-relevant features. However, reliability and robustness is especially important for high-risk fields such as clinical pain treatment. We therefore propose a verification pipeline, which consists of three steps. First, we classify facial expressions with a neural network. Next, we apply layer-wise relevance propagation to create pixel-based explanations. Finally, we quantify these visual explanations based on a bounding-box method with respect to facial regions. Although our results show that the neural network achieves state-of-the-art results, the evaluation of the visual explanations reveals that relevant facial regions may not be considered.
Tasks Facial Expression Recognition
Published 2020-02-14
URL https://arxiv.org/abs/2003.00828v1
PDF https://arxiv.org/pdf/2003.00828v1.pdf
PWC https://paperswithcode.com/paper/verifying-deep-learning-based-decisions-for

PyODDS: An End-to-end Outlier Detection System with Automated Machine Learning

Title PyODDS: An End-to-end Outlier Detection System with Automated Machine Learning
Authors Yuening Li, Daochen Zha, Praveen Kumar Venugopal, Na Zou, Xia Hu
Abstract Outlier detection is an important task for various data mining applications. Current outlier detection techniques are often manually designed for specific domains, requiring large human efforts of database setup, algorithm selection, and hyper-parameter tuning. To fill this gap, we present PyODDS, an automated end-to-end Python system for Outlier Detection with Database Support, which automatically optimizes an outlier detection pipeline for a new data source at hand. Specifically, we define the search space in the outlier detection pipeline, and produce a search strategy within the given search space. PyODDS enables end-to-end executions based on an Apache Spark backend server and a light-weight database. It also provides unified interfaces and visualizations for users with or without data science or machine learning background. In particular, we demonstrate PyODDS on several real-world datasets, with quantification analysis and visualization results.
Tasks Outlier Detection
Published 2020-03-12
URL https://arxiv.org/abs/2003.05602v1
PDF https://arxiv.org/pdf/2003.05602v1.pdf
PWC https://paperswithcode.com/paper/pyodds-an-end-to-end-outlier-detection-system-1
comments powered by Disqus