Paper Group ANR 127
Visualization approach to assess the robustness of neural networks for medical image classification. Cursive Multilingual Characters Recognition Based on Hard Geometric Features. Finding Syntactic Representations in Neural Stacks. Deep Reinforcement Learning for Distributed Uncoordinated Cognitive Radios Resource Allocation. Joint Object and State …
Visualization approach to assess the robustness of neural networks for medical image classification
| Title | Visualization approach to assess the robustness of neural networks for medical image classification |
| Authors | Elina Thibeau Sutre, Olivier Colliot, Didier Dormont, Ninon Burgos |
| Abstract | The use of neural networks for diagnosis classification is becoming more and more prevalent in the medical imaging community. However, deep learning method outputs remain hard to explain. Another difficulty is to choose among the large number of techniques developed to analyze how networks learn, as all present different limitations. In this paper, we extended the framework of Fong and Vedaldi [IEEE International Conference on Computer Vision (ICCV), 2017] to visualize the training of convolutional neural networks (CNNs) on 3D quantitative neuroimaging data. Our application focuses on the detection of Alzheimer’s disease with gray matter probability maps extracted from structural MRI. We first assessed the robustness of the visualization method by studying the coherence of the longitudinal patterns and regions identified by the network. We then studied the stability of the CNN training by computing visualization-based similarity indexes between different re-runs of the CNN. We demonstrated that the areas identified by the CNN were consistent with what is known of Alzheimer’s disease and that the visualization approach extract coherent longitudinal patterns. We also showed that the CNN training is not stable and that the areas identified mainly depend on the initialization and the training process. This issue may exist in many other medical studies using deep learning methods on datasets in which the number of samples is too small and the data dimension is high. This means that it may not be possible to rely on deep learning to detect stable regions of interest in this field yet. |
| Tasks | Image Classification |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08264v3 |
| https://arxiv.org/pdf/1911.08264v3.pdf | |
| PWC | https://paperswithcode.com/paper/visualization-approach-to-assess-the |
| Repo | |
| Framework | |
Cursive Multilingual Characters Recognition Based on Hard Geometric Features
| Title | Cursive Multilingual Characters Recognition Based on Hard Geometric Features |
| Authors | Amjad Rehman, Majid Harouni, Tanzila Saba |
| Abstract | The cursive nature of multilingual characters segmentation and recognition of Arabic, Persian, Urdu languages have attracted researchers from academia and industry. However, despite several decades of research, still multilingual characters classification accuracy is not up to the mark. This paper presents an automated approach for multilingual characters segmentation and recognition. The proposed methodology explores character based on their geometric features. However, due to uncertainty and without dictionary support few characters are over-divided. To expand the productivity of the proposed methodology a BPN is prepared with countless division focuses for cursive multilingual characters. Prepared BPN separates off base portioned indicates effectively with rapid upgrade character acknowledgment precision. For reasonable examination, only benchmark dataset is utilized. |
| Tasks | |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.08760v1 |
| http://arxiv.org/pdf/1904.08760v1.pdf | |
| PWC | https://paperswithcode.com/paper/190408760 |
| Repo | |
| Framework | |
Finding Syntactic Representations in Neural Stacks
| Title | Finding Syntactic Representations in Neural Stacks |
| Authors | William Merrill, Lenny Khazan, Noah Amsel, Yiding Hao, Simon Mendelsohn, Robert Frank |
| Abstract | Neural network architectures have been augmented with differentiable stacks in order to introduce a bias toward learning hierarchy-sensitive regularities. It has, however, proven difficult to assess the degree to which such a bias is effective, as the operation of the differentiable stack is not always interpretable. In this paper, we attempt to detect the presence of latent representations of hierarchical structure through an exploration of the unsupervised learning of constituency structure. Using a technique due to Shen et al. (2018a,b), we extract syntactic trees from the pushing behavior of stack RNNs trained on language modeling and classification objectives. We find that our models produce parses that reflect natural language syntactic constituencies, demonstrating that stack RNNs do indeed infer linguistically relevant hierarchical structure. |
| Tasks | Language Modelling |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01594v1 |
| https://arxiv.org/pdf/1906.01594v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-syntactic-representations-in-neural |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Distributed Uncoordinated Cognitive Radios Resource Allocation
| Title | Deep Reinforcement Learning for Distributed Uncoordinated Cognitive Radios Resource Allocation |
| Authors | Ankita Tondwalkar, Dr Andres Kwasinski |
| Abstract | This paper presents a novel deep reinforcement learning-based resource allocation technique for the multi-agent environment presented by a cognitive radio network that coexists through underlay dynamic spectrum access (DSA) with a primary network. The resource allocation technique presented in this work is distributed, not requiring coordination with other agents. The presented algorithm is the first deep reinforcement learning technique for which convergence to equilibrium policies can be shown in the non-stationary multi-agent environment that results from the uncoordinated dynamic interaction between radios through the shared wireless environment. Moreover, simulation results show that in a finite learning time the presented technique is able to find policies that yield performance within 3 % of an exhaustive search solution, finding the optimal policy in nearly 70 % of cases. Moreover, it is shown that standard single-agent deep reinforcement learning may not achieve convergence when used in a non-coordinated, coupled multi-radio scenario. |
| Tasks | |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1911.03366v2 |
| https://arxiv.org/pdf/1911.03366v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-distributed |
| Repo | |
| Framework | |
Joint Object and State Recognition using Language Knowledge
| Title | Joint Object and State Recognition using Language Knowledge |
| Authors | Ahmad Babaeian Jelodar, Yu Sun |
| Abstract | The state of an object is an important piece of knowledge in robotics applications. States and objects are intertwined together, meaning that object information can help recognize the state of an image and vice versa. This paper addresses the state identification problem in cooking related images and uses state and object predictions together to improve the classification accuracy of objects and their states from a single image. The pipeline presented in this paper includes a CNN with a double classification layer and the Concept-Net language knowledge graph on top. The language knowledge creates a semantic likelihood between objects and states. The resulting object and state confidences from the deep architecture are used together with object and state relatedness estimates from a language knowledge graph to produce marginal probabilities for objects and states. The marginal probabilities and confidences of objects (or states) are fused together to improve the final object (or state) classification results. Experiments on a dataset of cooking objects show that using a language knowledge graph on top of a deep neural network effectively enhances object and state classification. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.08843v1 |
| https://arxiv.org/pdf/1905.08843v1.pdf | |
| PWC | https://paperswithcode.com/paper/190508843 |
| Repo | |
| Framework | |
SemEval-2017 Task 4: Sentiment Analysis in Twitter
| Title | SemEval-2017 Task 4: Sentiment Analysis in Twitter |
| Authors | Sara Rosenthal, Noura Farra, Preslav Nakov |
| Abstract | This paper describes the fifth year of the Sentiment Analysis in Twitter task. SemEval-2017 Task 4 continues with a rerun of the subtasks of SemEval-2016 Task 4, which include identifying the overall sentiment of the tweet, sentiment towards a topic with classification on a two-point and on a five-point ordinal scale, and quantification of the distribution of sentiment towards a topic across a number of tweets: again on a two-point and on a five-point ordinal scale. Compared to 2016, we made two changes: (i) we introduced a new language, Arabic, for all subtasks, and (ii)~we made available information from the profiles of the Twitter users who posted the target tweets. The task continues to be very popular, with a total of 48 teams participating this year. |
| Tasks | Sentiment Analysis |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00741v1 |
| https://arxiv.org/pdf/1912.00741v1.pdf | |
| PWC | https://paperswithcode.com/paper/semeval-2017-task-4-sentiment-analysis-in-1 |
| Repo | |
| Framework | |
Recognition of Russian traffic signs in winter conditions. Solutions of the “Ice Vision” competition winners
| Title | Recognition of Russian traffic signs in winter conditions. Solutions of the “Ice Vision” competition winners |
| Authors | Artem L. Pavlov, Azat Davletshin, Alexey Kharlamov, Maksim S. Koriukin, Artem Vasenin, Pavel Solovev, Pavel Ostyakov, Pavel A. Karpyshev, George V. Ovchinnikov, Ivan V. Oseledets, Dzmitry Tsetserukou |
| Abstract | With the advancements of various autonomous car projects aiming to achieve SAE Level 5, real-time detection of traffic signs in real-life scenarios has become a highly relevant problem for the industry. Even though a great progress has been achieved in this field, there is still no clear consensus on what the state-of-the-art in this field is. Moreover, it is important to develop and test systems in various regions and conditions. This is why the “Ice Vision” competition has focused on the detection of Russian traffic signs in winter conditions. The IceVisionSet dataset used for this competition features real-world collection of lossless frame sequences with traffic sign annotations. The sequences were collected in varying conditions, including: different weather, camera exposure, illumination and moving speeds. In this work we describe the competition and present the solutions of the 3 top teams. |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07311v1 |
| https://arxiv.org/pdf/1909.07311v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognition-of-russian-traffic-signs-in |
| Repo | |
| Framework | |
PixelRL: Fully Convolutional Network with Reinforcement Learning for Image Processing
| Title | PixelRL: Fully Convolutional Network with Reinforcement Learning for Image Processing |
| Authors | Ryosuke Furuta, Naoto Inoue, Toshihiko Yamasaki |
| Abstract | This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing. After the introduction of the deep Q-network, deep RL has been achieving great success. However, the applications of deep reinforcement learning (RL) for image processing are still limited. Therefore, we extend deep RL to pixelRL for various image processing applications. In pixelRL, each pixel has an agent, and the agent changes the pixel value by taking an action. We also propose an effective learning method for pixelRL that significantly improves the performance by considering not only the future states of the own pixel but also those of the neighbor pixels. The proposed method can be applied to some image processing tasks that require pixel-wise manipulations, where deep RL has never been applied. Besides, it is possible to visualize what kind of operation is employed for each pixel at each iteration, which would help us understand why and how such an operation is chosen. We also believe that our technology can enhance the explainability and interpretability of the deep neural networks. In addition, because the operations executed at each pixels are visualized, we can change or modify the operations if necessary. We apply the proposed method to a variety of image processing tasks: image denoising, image restoration, local color enhancement, and saliency-driven image editing. Our experimental results demonstrate that the proposed method achieves comparable or better performance, compared with the state-of-the-art methods based on supervised learning. The source code is available on https://github.com/rfuruta/pixelRL. |
| Tasks | Denoising, Image Denoising, Image Restoration, Local Color Enhancement |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07190v1 |
| https://arxiv.org/pdf/1912.07190v1.pdf | |
| PWC | https://paperswithcode.com/paper/pixelrl-fully-convolutional-network-with |
| Repo | |
| Framework | |
Spatial-Frequency Domain Nonlocal Total Variation for Image Denoising
| Title | Spatial-Frequency Domain Nonlocal Total Variation for Image Denoising |
| Authors | Haijuan Hu, Jacques Froment, Baoyan Wang, Xiequan Fan |
| Abstract | Following the pioneering works of Rudin, Osher and Fatemi on total variation (TV) and of Buades, Coll and Morel on non-local means (NL-means), the last decade has seen a large number of denoising methods mixing these two approaches, starting with the nonlocal total variation (NLTV) model. The present article proposes an analysis of the NLTV model for image denoising as well as a number of improvements, the most important of which being to apply the denoising both in the space domain and in the Fourier domain, in order to exploit the complementarity of the representation of image data in both domains. A local version obtained by a regionwise implementation followed by an aggregation process, called Local Spatial-Frequency NLTV (L- SFNLTV) model, is finally proposed as a new reference algorithm for image denoising among the family of approaches mixing TV and NL operators. The experiments show the great performance of L-SFNLTV, both in terms of image quality and of computational speed, comparing with other recently proposed NLTV-related methods. |
| Tasks | Denoising, Image Denoising |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02357v1 |
| https://arxiv.org/pdf/1912.02357v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-frequency-domain-nonlocal-total |
| Repo | |
| Framework | |
Temporal Network Sampling
| Title | Temporal Network Sampling |
| Authors | Nesreen K. Ahmed, Nick Duffield, Ryan A. Rossi |
| Abstract | Temporal networks representing a stream of timestamped edges are seemingly ubiquitous in the real-world. However, the massive size and continuous nature of these networks make them fundamentally challenging to analyze and leverage for descriptive and predictive modeling tasks. In this work, we propose a general framework for temporal network sampling with unbiased estimation. We develop online, single-pass sampling algorithms and unbiased estimators for temporal network sampling. The proposed algorithms enable fast, accurate, and memory-efficient statistical estimation of temporal network patterns and properties. In addition, we propose a temporally decaying sampling algorithm with unbiased estimators for studying networks that evolve in continuous time, where the strength of links is a function of time, and the motif patterns are temporally-weighted. In contrast to the prior notion of a $\bigtriangleup t$-temporal motif, the proposed formulation and algorithms for counting temporally weighted motifs are useful for forecasting tasks in networks such as predicting future links, or a future time-series variable of nodes and links. Finally, extensive experiments on a variety of temporal networks from different domains demonstrate the effectiveness of the proposed algorithms. |
| Tasks | Time Series |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08657v1 |
| https://arxiv.org/pdf/1910.08657v1.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-network-sampling |
| Repo | |
| Framework | |
Mumford-Shah functionals on graphs and their asymptotics
| Title | Mumford-Shah functionals on graphs and their asymptotics |
| Authors | Marco Caroccia, Antonin Chambolle, Dejan Slepčev |
| Abstract | We consider adaptations of the Mumford-Shah functional to graphs. These are based on discretizations of nonlocal approximations to the Mumford-Shah functional. Motivated by applications in machine learning we study the random geometric graphs associated to random samples of a measure. We establish the conditions on the graph constructions under which the minimizers of graph Mumford-Shah functionals converge to a minimizer of a continuum Mumford-Shah functional. Furthermore we explicitly identify the limiting functional. Moreover we describe an efficient algorithm for computing the approximate minimizers of the graph Mumford-Shah functional. |
| Tasks | |
| Published | 2019-06-22 |
| URL | https://arxiv.org/abs/1906.09521v2 |
| https://arxiv.org/pdf/1906.09521v2.pdf | |
| PWC | https://paperswithcode.com/paper/mumford-shah-functionals-on-graphs-and-their |
| Repo | |
| Framework | |
Energy-Aware Multi-Server Mobile Edge Computing: A Deep Reinforcement Learning Approach
| Title | Energy-Aware Multi-Server Mobile Edge Computing: A Deep Reinforcement Learning Approach |
| Authors | Navid Naderializadeh, Morteza Hashemi |
| Abstract | We investigate the problem of computation offloading in a mobile edge computing architecture, where multiple energy-constrained users compete to offload their computational tasks to multiple servers through a shared wireless medium. We propose a multi-agent deep reinforcement learning algorithm, where each server is equipped with an agent, observing the status of its associated users and selecting the best user for offloading at each step. We consider computation time (i.e., task completion time) and system lifetime as two key performance indicators, and we numerically demonstrate that our approach outperforms baseline algorithms in terms of the trade-off between computation time and system lifetime. |
| Tasks | |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.10485v1 |
| https://arxiv.org/pdf/1912.10485v1.pdf | |
| PWC | https://paperswithcode.com/paper/energy-aware-multi-server-mobile-edge |
| Repo | |
| Framework | |
Normalyzing Numeronyms – A NLP approach
| Title | Normalyzing Numeronyms – A NLP approach |
| Authors | Avishek Garain, Sainik Kumar Mahata, Subhabrata Dutta |
| Abstract | This paper presents a method to apply Natural Language Processing for normalizing numeronyms to make them understandable by humans. We approach the problem through a two-step mechanism. We make use of the state of the art Levenshtein distance of words. We then apply Cosine Similarity for selection of the normalized text and reach greater accuracy in solving the problem. Our approach garners accuracy figures of 71% and 72% for Bengali and English language, respectively. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13356v2 |
| https://arxiv.org/pdf/1907.13356v2.pdf | |
| PWC | https://paperswithcode.com/paper/normalyzing-numeronyms-a-nlp-approach |
| Repo | |
| Framework | |
Competitive Statistical Estimation with Strategic Data Sources
| Title | Competitive Statistical Estimation with Strategic Data Sources |
| Authors | Tyler Westenbroek, Roy Dong, Lillian J. Ratliff, S. Shankar Sastry |
| Abstract | In recent years, data has played an increasingly important role in the economy as a good in its own right. In many settings, data aggregators cannot directly verify the quality of the data they purchase, nor the effort exerted by data sources when creating the data. Recent work has explored mechanisms to ensure that the data sources share high quality data with a single data aggregator, addressing the issue of moral hazard. Oftentimes, there is a unique, socially efficient solution. In this paper, we consider data markets where there is more than one data aggregator. Since data can be cheaply reproduced and transmitted once created, data sources may share the same data with more than one aggregator, leading to free-riding between data aggregators. This coupling can lead to non-uniqueness of equilibria and social inefficiency. We examine a particular class of mechanisms that have received study recently in the literature, and we characterize all the generalized Nash equilibria of the resulting data market. We show that, in contrast to the single-aggregator case, there is either infinitely many generalized Nash equilibria or none. We also provide necessary and sufficient conditions for all equilibria to be socially inefficient. In our analysis, we identify the components of these mechanisms which give rise to these undesirable outcomes, showing the need for research into mechanisms for competitive settings with multiple data purchasers and sellers. |
| Tasks | |
| Published | 2019-04-29 |
| URL | http://arxiv.org/abs/1904.12768v1 |
| http://arxiv.org/pdf/1904.12768v1.pdf | |
| PWC | https://paperswithcode.com/paper/competitive-statistical-estimation-with |
| Repo | |
| Framework | |
Using Natural Language Processing to Develop an Automated Orthodontic Diagnostic System
| Title | Using Natural Language Processing to Develop an Automated Orthodontic Diagnostic System |
| Authors | Tomoyuki Kajiwara, Chihiro Tanikawa, Yuujin Shimizu, Chenhui Chu, Takashi Yamashiro, Hajime Nagahara |
| Abstract | We work on the task of automatically designing a treatment plan from the findings included in the medical certificate written by the dentist. To develop an artificial intelligence system that deals with free-form certificates written by dentists, we annotate the findings and utilized the natural language processing approach. As a result of the experiment using 990 certificates, 0.585 F1-score was achieved for the task of extracting orthodontic problems from findings, and 0.584 correlation coefficient with the human ranking was achieved for the treatment prioritization task. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13601v1 |
| https://arxiv.org/pdf/1905.13601v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-natural-language-processing-to-develop |
| Repo | |
| Framework | |
