January 26, 2020

3270 words 16 mins read

Paper Group ANR 1425

Computed tomography data collection of the complete human mandible and valid clinical ground truth models. Visual Interaction with Deep Learning Models through Collaborative Semantic Inference. Generating an Overview Report over Many Documents. DSRGAN: Explicitly Learning Disentangled Representation of Underlying Structure and Rendering for Image G …

Computed tomography data collection of the complete human mandible and valid clinical ground truth models


Title	Computed tomography data collection of the complete human mandible and valid clinical ground truth models
Authors	Jürgen Wallner, Irene Mischak, Jan Egger
Abstract	Image-based algorithmic software segmentation is an increasingly important topic in many medical fields. Algorithmic segmentation is used for medical three-dimensional visualization, diagnosis or treatment support, especially in complex medical cases. However, accessible medical databases are limited, and valid medical ground truth databases for the evaluation of algorithms are rare and usually comprise only a few images. Inaccuracy or invalidity of medical ground truth data and image-based artefacts also limit the creation of such databases, which is especially relevant for CT data sets of the maxillomandibular complex. This contribution provides a unique and accessible data set of the complete mandible, including 20 valid ground truth segmentation models originating from 10 CT scans from clinical practice without artefacts or faulty slices. From each CT scan, two 3D ground truth models were created by clinical experts through independent manual slice-by-slice segmentation, and the models were statistically compared to prove their validity. These data could be used to conduct serial image studies of the human mandible, evaluating segmentation algorithms and developing adequate image tools.
Tasks
Published	2019-02-14
URL	http://arxiv.org/abs/1902.05255v1
PDF	http://arxiv.org/pdf/1902.05255v1.pdf
PWC	https://paperswithcode.com/paper/computed-tomography-data-collection-of-the
Repo
Framework

Visual Interaction with Deep Learning Models through Collaborative Semantic Inference


Title	Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
Authors	Sebastian Gehrmann, Hendrik Strobelt, Robert Krüger, Hanspeter Pfister, Alexander M. Rush
Abstract	Automation of tasks can have critical consequences when humans lose agency over decision processes. Deep learning models are particularly susceptible since current black-box approaches lack explainable reasoning. We argue that both the visual interface and model structure of deep learning systems need to take into account interaction design. We propose a framework of collaborative semantic inference (CSI) for the co-design of interactions and models to enable visual collaboration between humans and algorithms. The approach exposes the intermediate reasoning process of models which allows semantic interactions with the visual metaphors of a problem, which means that a user can both understand and control parts of the model reasoning process. We demonstrate the feasibility of CSI with a co-designed case study of a document summarization system.
Tasks	Document Summarization
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10739v1
PDF	https://arxiv.org/pdf/1907.10739v1.pdf
PWC	https://paperswithcode.com/paper/visual-interaction-with-deep-learning-models
Repo
Framework

Generating an Overview Report over Many Documents


Title	Generating an Overview Report over Many Documents
Authors	Jingwen Wang, Hao Zhang, Cheng Zhang, Wenjing Yang, Liqun Shao, Jie Wang
Abstract	How to efficiently generate an accurate, well-structured overview report (ORPT) over thousands of related documents is challenging. A well-structured ORPT consists of sections of multiple levels (e.g., sections and subsections). None of the existing multi-document summarization (MDS) algorithms is directed toward this task. To overcome this obstacle, we present NDORGS (Numerous Documents’ Overview Report Generation Scheme) that integrates text filtering, keyword scoring, single-document summarization (SDS), topic modeling, MDS, and title generation to generate a coherent, well-structured ORPT. We then devise a multi-criteria evaluation method using techniques of text mining and multi-attribute decision making on a combination of human judgments, running time, information coverage, and topic diversity. We evaluate ORPTs generated by NDORGS on two large corpora of documents, where one is classified and the other unclassified. We show that, using Saaty’s pairwise comparison 9-point scale and under TOPSIS, the ORPTs generated on SDS’s with the length of 20% of the original documents are the best overall on both datasets.
Tasks	Decision Making, Document Summarization, Multi-Document Summarization
Published	2019-08-17
URL	https://arxiv.org/abs/1908.06216v1
PDF	https://arxiv.org/pdf/1908.06216v1.pdf
PWC	https://paperswithcode.com/paper/generating-an-overview-report-over-many
Repo
Framework

DSRGAN: Explicitly Learning Disentangled Representation of Underlying Structure and Rendering for Image Generation without Tuple Supervision


Title	DSRGAN: Explicitly Learning Disentangled Representation of Underlying Structure and Rendering for Image Generation without Tuple Supervision
Authors	Guang-Yuan Hao, Hong-Xing Yu, Wei-Shi Zheng
Abstract	We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision. The setting is significant since tuple supervision is costly and sometimes even unavailable. However, the task is highly unconstrained and thus ill-posed. To address this problem, we propose to introduce an auxiliary domain which shares a common underlying-structure space with the target domain, and we make a partially shared latent space assumption. The key idea is to encourage the partially shared latent variable to represent the similar underlying spatial structures in both domains, while the two domain-specific latent variables will be unavoidably arranged to present renderings of two domains respectively. This is achieved by designing two parallel generative networks with a common Progressive Rendering Architecture (PRA), which constrains both generative networks’ behaviors to model shared underlying structure and to model spatially dependent relation between rendering and underlying structure. Thus, we propose DSRGAN (GANs for Disentangling Underlying Structure and Rendering) to instantiate our method. We also propose a quantitative criterion (the Normalized Disentanglability) to quantify disentanglability. Comparison to the state-of-the-art methods shows that DSRGAN can significantly outperform them in disentanglability.
Tasks	Image Generation
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13501v1
PDF	https://arxiv.org/pdf/1909.13501v1.pdf
PWC	https://paperswithcode.com/paper/dsrgan-explicitly-learning-disentangled
Repo
Framework

Autoencoding Binary Classifiers for Supervised Anomaly Detection


Title	Autoencoding Binary Classifiers for Supervised Anomaly Detection
Authors	Yuki Yamanaka, Tomoharu Iwata, Hiroshi Takahashi, Masanori Yamada, Sekitoshi Kanai
Abstract	We propose the Autoencoding Binary Classifiers (ABC), a novel supervised anomaly detector based on the Autoencoder (AE). There are two main approaches in anomaly detection: supervised and unsupervised. The supervised approach accurately detects the known anomalies included in training data, but it cannot detect the unknown anomalies. Meanwhile, the unsupervised approach can detect both known and unknown anomalies that are located away from normal data points. However, it does not detect known anomalies as accurately as the supervised approach. Furthermore, even if we have labeled normal data points and anomalies, the unsupervised approach cannot utilize these labels. The ABC is a probabilistic binary classifier that effectively exploits the label information, where normal data points are modeled using the AE as a component. By maximizing the likelihood, the AE in the proposed ABC is trained to minimize the reconstruction error for normal data points, and to maximize it for known anomalies. Since our approach becomes able to reconstruct the normal data points accurately and fails to reconstruct the known and unknown anomalies, it can accurately discriminate both known and unknown anomalies from normal data points. Experimental results show that the ABC achieves higher detection performance than existing supervised and unsupervised methods.
Tasks	Anomaly Detection
Published	2019-03-26
URL	http://arxiv.org/abs/1903.10709v1
PDF	http://arxiv.org/pdf/1903.10709v1.pdf
PWC	https://paperswithcode.com/paper/autoencoding-binary-classifiers-for
Repo
Framework

When can unlabeled data improve the learning rate?


Title	When can unlabeled data improve the learning rate?
Authors	Christina Göpfert, Shai Ben-David, Olivier Bousquet, Sylvain Gelly, Ilya Tolstikhin, Ruth Urner
Abstract	In semi-supervised classification, one is given access both to labeled and unlabeled data. As unlabeled data is typically cheaper to acquire than labeled data, this setup becomes advantageous as soon as one can exploit the unlabeled data in order to produce a better classifier than with labeled data alone. However, the conditions under which such an improvement is possible are not fully understood yet. Our analysis focuses on improvements in the minimax learning rate in terms of the number of labeled examples (with the number of unlabeled examples being allowed to depend on the number of labeled ones). We argue that for such improvements to be realistic and indisputable, certain specific conditions should be satisfied and previous analyses have failed to meet those conditions. We then demonstrate examples where these conditions can be met, in particular showing rate changes from $1/\sqrt{\ell}$ to $e^{-c\ell}$ and from $1/\sqrt{\ell}$ to $1/\ell$. These results improve our understanding of what is and isn’t possible in semi-supervised learning.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11866v1
PDF	https://arxiv.org/pdf/1905.11866v1.pdf
PWC	https://paperswithcode.com/paper/when-can-unlabeled-data-improve-the-learning
Repo
Framework

EmotionX-IDEA: Emotion BERT – an Affectional Model for Conversation


Title	EmotionX-IDEA: Emotion BERT – an Affectional Model for Conversation
Authors	Yen-Hao Huang, Ssu-Rui Lee, Mau-Yun Ma, Yi-Hsin Chen, Ya-Wen Yu, Yi-Shin Chen
Abstract	In this paper, we investigate the emotion recognition ability of the pre-training language model, namely BERT. By the nature of the framework of BERT, a two-sentence structure, we adapt BERT to continues dialogue emotion prediction tasks, which rely heavily on the sentence-level context-aware understanding. The experiments show that by mapping the continues dialogue into a causal utterance pair, which is constructed by the utterance and the reply utterance, models can better capture the emotions of the reply utterance. The present method has achieved 0.815 and 0.885 micro F1 score in the testing dataset of Friends and EmotionPush, respectively.
Tasks	Emotion Recognition, Language Modelling
Published	2019-08-17
URL	https://arxiv.org/abs/1908.06264v1
PDF	https://arxiv.org/pdf/1908.06264v1.pdf
PWC	https://paperswithcode.com/paper/emotionx-idea-emotion-bert-an-affectional
Repo
Framework

Impact of perfusion ROI detection to the quality of CBV perfusion map


Title	Impact of perfusion ROI detection to the quality of CBV perfusion map
Authors	Svitlana Alkhimova
Abstract	The object of research in this study is quality of CBV perfusion map, considering detection of perfusion ROI as a key component in processing of dynamic susceptibility contrast magnetic resonance images of a human head. CBV map is generally accepted to be the best among others to evaluate location and size of stroke lesions and angiogenesis of brain tumors. Its poor accuracy can cause failed results for both quantitative measurements and visual assessment of cerebral blood volume. The impact of perfusion ROI detection on the quality of maps was analyzed through comparison of maps produced from threshold and reference images of the same datasets from 12 patients with cerebrovascular disease. Brain perfusion ROI was placed to exclude low intensity (air and non-brain tissues regions) and high intensity (cerebrospinal fluid regions) pixels. Maps were produced using area under the curve and deconvolution methods. For both methods compared maps were primarily correlational according to Pearson correlation analysis: r=0.8752 and r=0.8706 for area under the curve and deconvolution, respectively, p<2.2*10^-16. In spite of this, for both methods scatter plots had data points associated with missed blood regions and regression lines indicated presence of scale and offset errors for maps produced from threshold images. Obtained results indicate that thresholding is an ineffective way to detect brain perfusion ROI, which usage can cause degradation of CBV map quality. Perfusion ROI detection should be standardized and accepted into validation protocols of new systems for perfusion data analysis.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1912.05471v1
PDF	https://arxiv.org/pdf/1912.05471v1.pdf
PWC	https://paperswithcode.com/paper/impact-of-perfusion-roi-detection-to-the
Repo
Framework

Interactive Subspace Exploration on Generative Image Modelling


Title	Interactive Subspace Exploration on Generative Image Modelling
Authors	Toby Chong Long Hin, I-Chao Shen, Issei Sato, Takeo Igarashi
Abstract	Generative image modeling techniques such as GAN demonstrate highly convincing image generation result. However, user interaction is often necessary to obtain the desired results. Existing attempts add interactivity but require either tailored architectures or extra data. We present a human-in-the-optimization method that allows users to directly explore and search the latent vector space of generative image modeling. Our system provides multiple candidates by sampling the latent vector space, and the user selects the best blending weights within the subspace using multiple sliders. In addition, the user can express their intention through image editing tools. The system samples latent vectors based on inputs and presents new candidates to the user iteratively. An advantage of our formulation is that one can apply our method to arbitrary pre-trained model without developing specialized architecture or data. We demonstrate our method with various generative image modeling applications, and show superior performance in a comparative user study with prior art iGAN \cite{iGAN2016}.
Tasks	Image Generation
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09840v2
PDF	https://arxiv.org/pdf/1906.09840v2.pdf
PWC	https://paperswithcode.com/paper/interactive-subspace-exploration-on
Repo
Framework

Limiting Network Size within Finite Bounds for Optimization


Title	Limiting Network Size within Finite Bounds for Optimization
Authors	Linu Pinto, Dr. Sasi Gopalan
Abstract	Largest theoretical contribution to Neural Networks comes from VC Dimension which characterizes the sample complexity of classification model in a probabilistic view and are widely used to study the generalization error. So far in the literature the VC Dimension has only been used to approximate the generalization error bounds on different Neural Network architectures. VC Dimension has not yet been implicitly or explicitly stated to fix the network size which is important as the wrong configuration could lead to high computation effort in training and leads to over fitting. So there is a need to bound these units so that task can be computed with only sufficient number of parameters. For binary classification tasks shallow networks are used as they have universal approximation property and it is enough to size the hidden layer width for such networks. The paper brings out a theoretical justification on required attribute size and its corresponding hidden layer dimension for a given sample set that gives an optimal binary classification results with minimum training complexity in a single layered feed forward network framework. The paper also establishes proof on the existence of bounds on the width of the hidden layer and its range subjected to certain conditions. Findings in this paper are experimentally analyzed on three different dataset using Mathlab 2018 (b) software.
Tasks
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02809v1
PDF	http://arxiv.org/pdf/1903.02809v1.pdf
PWC	https://paperswithcode.com/paper/limiting-network-size-within-finite-bounds
Repo
Framework

Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods


Title	Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods
Authors	Ching-An Cheng, Xinyan Yan, Byron Boots
Abstract	Policy gradient methods have demonstrated success in reinforcement learning tasks that have high-dimensional continuous state and action spaces. However, policy gradient methods are also notoriously sample inefficient. This can be attributed, at least in part, to the high variance in estimating the gradient of the task objective with Monte Carlo methods. Previous research has endeavored to contend with this problem by studying control variates (CVs) that can reduce the variance of estimates without introducing bias, including the early use of baselines, state dependent CVs, and the more recent state-action dependent CVs. In this work, we analyze the properties and drawbacks of previous CV techniques and, surprisingly, we find that these works have overlooked an important fact that Monte Carlo gradient estimates are generated by trajectories of states and actions. We show that ignoring the correlation across the trajectories can result in suboptimal variance reduction, and we propose a simple fix: a class of “trajectory-wise” CVs, that can further drive down the variance. We show that constructing trajectory-wise CVs can be done recursively and requires only learning state-action value functions like the previous CVs for policy gradient. We further prove that the proposed trajectory-wise CVs are optimal for variance reduction under reasonable assumptions.
Tasks	Policy Gradient Methods
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03263v1
PDF	https://arxiv.org/pdf/1908.03263v1.pdf
PWC	https://paperswithcode.com/paper/trajectory-wise-control-variates-for-variance
Repo
Framework

Convolutional Neural Networks for Space-Time Block Coding Recognition


Title	Convolutional Neural Networks for Space-Time Block Coding Recognition
Authors	Wenjun Yan, Qing Ling, Limin Zhang
Abstract	We apply the latest advances in machine learning with deep neural networks to the tasks of radio modulation recognition, channel coding recognition, and spectrum monitoring. This paper first proposes an identification algorithm for space-time block coding of a signal. The feature between spatial multiplexing and Alamouti signals is extracted by adapting convolutional neural networks after preprocessing the received sequence. Unlike other algorithms, this method requires no prior information of channel coefficients and noise power, and consequently is well-suited for noncooperative contexts. Results show that the proposed algorithm performs well even at a low signal-to-noise ratio
Tasks
Published	2019-10-19
URL	https://arxiv.org/abs/1910.09952v2
PDF	https://arxiv.org/pdf/1910.09952v2.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-for-space-time
Repo
Framework

How Should an Agent Practice?


Title	How Should an Agent Practice?
Authors	Janarthanan Rajendran, Richard Lewis, Vivek Veeriah, Honglak Lee, Satinder Singh
Abstract	We present a method for learning intrinsic reward functions to drive the learning of an agent during periods of practice in which extrinsic task rewards are not available. During practice, the environment may differ from the one available for training and evaluation with extrinsic rewards. We refer to this setup of alternating periods of practice and objective evaluation as practice-match, drawing an analogy to regimes of skill acquisition common for humans in sports and games. The agent must effectively use periods in the practice environment so that performance improves during matches. In the proposed method the intrinsic practice reward is learned through a meta-gradient approach that adapts the practice reward parameters to reduce the extrinsic match reward loss computed from matches. We illustrate the method on a simple grid world, and evaluate it in two games in which the practice environment differs from match: Pong with practice against a wall without an opponent, and PacMan with practice in a maze without ghosts. The results show gains from learning in practice in addition to match periods over learning in matches only.
Tasks
Published	2019-12-15
URL	https://arxiv.org/abs/1912.07045v1
PDF	https://arxiv.org/pdf/1912.07045v1.pdf
PWC	https://paperswithcode.com/paper/how-should-an-agent-practice
Repo
Framework

Automated Generation of Test Models from Semi-Structured Requirements


Title	Automated Generation of Test Models from Semi-Structured Requirements
Authors	Jannik Fischbach, Maximilian Junker, Andreas Vogelsang, Dietmar Freudenstein
Abstract	[Context:] Model-based testing is an instrument for automated generation of test cases. It requires identifying requirements in documents, understanding them syntactically and semantically, and then translating them into a test model. One light-weight language for these test models are Cause-Effect-Graphs (CEG) that can be used to derive test cases. [Problem:] The creation of test models is laborious and we lack an automated solution that covers the entire process from requirement detection to test model creation. In addition, the majority of requirements is expressed in natural language (NL), which is hard to translate to test models automatically. [Principal Idea:] We build on the fact that not all NL requirements are equally unstructured. We found that 14 % of the lines in requirements documents of our industry partner contain “pseudo-code”-like descriptions of business rules. We apply Machine Learning to identify such semi-structured requirements descriptions and propose a rule-based approach for their translation into CEGs. [Contribution:] We make three contributions: (1) an algorithm for the automatic detection of semi-structured requirements descriptions in documents, (2) an algorithm for the automatic translation of the identified requirements into a CEG and (3) a study demonstrating that our proposed solution leads to 86 % time savings for test model creation without loss of quality.
Tasks
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08810v1
PDF	https://arxiv.org/pdf/1908.08810v1.pdf
PWC	https://paperswithcode.com/paper/automated-generation-of-test-models-from-semi
Repo
Framework

Fast-DENSER++: Evolving Fully-Trained Deep Artificial Neural Networks


Title	Fast-DENSER++: Evolving Fully-Trained Deep Artificial Neural Networks
Authors	Filipe Assunção, Nuno Lourenço, Penousal Machado, Bernardete Ribeiro
Abstract	This paper proposes a new extension to Deep Evolutionary Network Structured Evolution (DENSER), called Fast-DENSER++ (F-DENSER++). The vast majority of NeuroEvolution methods that optimise Deep Artificial Neural Networks (DANNs) only evaluate the candidate solutions for a fixed amount of epochs; this makes it difficult to effectively assess the learning strategy, and requires the best generated network to be further trained after evolution. F-DENSER++ enables the training time of the candidate solutions to grow continuously as necessary, i.e., in the initial generations the candidate solutions are trained for shorter times, and as generations proceed it is expected that longer training cycles enable better performances. Consequently, the models discovered by F-DENSER++ are fully-trained DANNs, and are ready for deployment after evolution, without the need for further training. The results demonstrate the ability of F-DENSER++ to effectively generate fully-trained DANNs; by the end of evolution, whilst the average performance of the models generated by F-DENSER++ is of 88.73%, the performance of the models generated by the previous version of DENSER (Fast-DENSER) is 86.91% (statistically significant), which increases to 87.76% when allowed to train for longer.
Tasks
Published	2019-05-08
URL	https://arxiv.org/abs/1905.02969v1
PDF	https://arxiv.org/pdf/1905.02969v1.pdf
PWC	https://paperswithcode.com/paper/fast-denser-evolving-fully-trained-deep
Repo
Framework