Paper Group ANR 400
Dense Dilated Network with Probability Regularized Walk for Vessel Detection. Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis. Efficient crowdsourcing of crowd-generated microtasks. A new algorithm for shape matching and pattern recognition using dynamic programming. Evalua …
Dense Dilated Network with Probability Regularized Walk for Vessel Detection
| Title | Dense Dilated Network with Probability Regularized Walk for Vessel Detection |
| Authors | Lei Mou, Li Chen, Jun Cheng, Zaiwang Gu, Yitian Zhao, Jiang Liu |
| Abstract | The detection of retinal vessel is of great importance in the diagnosis and treatment of many ocular diseases. Many methods have been proposed for vessel detection. However, most of the algorithms neglect the connectivity of the vessels, which plays an important role in the diagnosis. In this paper, we propose a novel method for retinal vessel detection. The proposed method includes a dense dilated network to get an initial detection of the vessels and a probability regularized walk algorithm to address the fracture issue in the initial detection. The dense dilated network integrates newly proposed dense dilated feature extraction blocks into an encoder-decoder structure to extract and accumulate features at different scales. A multiscale Dice loss function is adopted to train the network. To improve the connectivity of the segmented vessels, we also introduce a probability regularized walk algorithm to connect the broken vessels. The proposed method has been applied on three public data sets: DRIVE, STARE and CHASE_DB1. The results show that the proposed method outperforms the state-of-the-art methods in accuracy, sensitivity, specificity and also are under receiver operating characteristic curve. |
| Tasks | |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12010v1 |
| https://arxiv.org/pdf/1910.12010v1.pdf | |
| PWC | https://paperswithcode.com/paper/dense-dilated-network-with-probability |
| Repo | |
| Framework | |
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis
| Title | Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis |
| Authors | Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama |
| Abstract | The notion of flat minima has played a key role in the generalization studies of deep learning models. However, existing definitions of the flatness are known to be sensitive to the rescaling of parameters. The issue suggests that the previous definitions of the flatness might not be a good measure of generalization, because generalization is invariant to such rescalings. In this paper, from the PAC-Bayesian perspective, we scrutinize the discussion concerning the flat minima and introduce the notion of normalized flat minima, which is free from the known scale dependence issues. Additionally, we highlight the scale dependence of existing matrix-norm based generalization error bounds similar to the existing flat minima definitions. Our modified notion of the flatness does not suffer from the insufficiency, either, suggesting it might provide better hierarchy in the hypothesis class. |
| Tasks | |
| Published | 2019-01-15 |
| URL | http://arxiv.org/abs/1901.04653v2 |
| http://arxiv.org/pdf/1901.04653v2.pdf | |
| PWC | https://paperswithcode.com/paper/normalized-flat-minima-exploring-scale |
| Repo | |
| Framework | |
Efficient crowdsourcing of crowd-generated microtasks
| Title | Efficient crowdsourcing of crowd-generated microtasks |
| Authors | Abigail Hotaling, James P. Bagrow |
| Abstract | Allowing members of the crowd to propose novel microtasks for one another is an effective way to combine the efficiencies of traditional microtask work with the inventiveness and hypothesis generation potential of human workers. However, microtask proposal leads to a growing set of tasks that may overwhelm limited crowdsourcer resources. Crowdsourcers can employ methods to utilize their resources efficiently, but algorithmic approaches to efficient crowdsourcing generally require a fixed task set of known size. In this paper, we introduce cost forecasting as a means for a crowdsourcer to use efficient crowdsourcing algorithms with a growing set of microtasks. Cost forecasting allows the crowdsourcer to decide between eliciting new tasks from the crowd or receiving responses to existing tasks based on whether or not new tasks will cost less to complete than existing tasks, efficiently balancing resources as crowdsourcing occurs. Experiments with real and synthetic crowdsourcing data show that cost forecasting leads to improved accuracy. Accuracy and efficiency gains for crowd-generated microtasks hold the promise to further leverage the creativity and wisdom of the crowd, with applications such as generating more informative and diverse training data for machine learning applications and improving the performance of user-generated content and question-answering platforms. |
| Tasks | Question Answering |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.05045v1 |
| https://arxiv.org/pdf/1912.05045v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-crowdsourcing-of-crowd-generated |
| Repo | |
| Framework | |
A new algorithm for shape matching and pattern recognition using dynamic programming
| Title | A new algorithm for shape matching and pattern recognition using dynamic programming |
| Authors | Noreddine Gherabi, Bahaj Mohamed |
| Abstract | We propose a new method for shape recognition and retrieval based on dynamic programming. Our approach uses the dynamic programming algorithm to compute the optimal score and to find the optimal alignment between two strings. First, each contour of shape is represented by a set of points. After alignment and matching between two shapes, the contours are transformed into a string of symbols and numbers. Finally we find the best alignment of two complete strings and compute the optimal cost of similarity. In general, dynamic programming has two phases: the forward phase and the backward phase. In the forward phase, we compute the optimal cost for each subproblem. In the backward phase, we reconstruct the solution that gives the optimal cost. Our algorithm is tested in a database that contains various shapes such as MPEG-7. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.13219v1 |
| http://arxiv.org/pdf/1904.13219v1.pdf | |
| PWC | https://paperswithcode.com/paper/190413219 |
| Repo | |
| Framework | |
Evaluating Tag Recommendations for E-Book Annotation Using a Semantic Similarity Metric
| Title | Evaluating Tag Recommendations for E-Book Annotation Using a Semantic Similarity Metric |
| Authors | Emanuel Lacic, Dominik Kowald, Dieter Theiler, Matthias Traub, Lucky Kuffer, Stefanie Lindstaedt, Elisabeth Lex |
| Abstract | In this paper, we present our work to support publishers and editors in finding descriptive tags for e-books through tag recommendations. We propose a hybrid tag recommendation system for e-books, which leverages search query terms from Amazon users and e-book metadata, which is assigned by publishers and editors. Our idea is to mimic the vocabulary of users in Amazon, who search for and review e-books, and to combine these search terms with editor tags in a hybrid tag recommendation approach. In total, we evaluate 19 tag recommendation algorithms on the review content of Amazon users, which reflects the readers’ vocabulary. Our results show that we can improve the performance of tag recommender systems for e-books both concerning tag recommendation accuracy, diversity as well as a novel semantic similarity metric, which we also propose in this paper. |
| Tasks | Recommendation Systems, Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04042v1 |
| https://arxiv.org/pdf/1908.04042v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-tag-recommendations-for-e-book |
| Repo | |
| Framework | |
SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with Spikes
| Title | SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with Spikes |
| Authors | Johannes Christian Thiele, Olivier Bichler, Antoine Dupret |
| Abstract | Event-based neuromorphic systems promise to reduce the energy consumption of deep learning tasks by replacing expensive floating point operations on dense matrices by low power sparse and asynchronous operations on spike events. While these systems can be trained increasingly well using approximations of the back-propagation algorithm, these implementations usually require high precision errors for training and are therefore incompatible with the typical communication infrastructure of neuromorphic circuits. In this work, we analyze how the gradient can be discretized into spike events when training a spiking neural network. To accelerate our simulation, we show that using a special implementation of the integrate-and-fire neuron allows us to describe the accumulated activations and errors of the spiking neural network in terms of an equivalent artificial neural network, allowing us to largely speed up training compared to an explicit simulation of all spike events. This way we are able to demonstrate that even for deep networks, the gradients can be discretized sufficiently well with spikes if the gradient is properly rescaled. This form of spike-based backpropagation enables us to achieve equivalent or better accuracies on the MNIST and CIFAR10 dataset than comparable state-of-the-art spiking neural networks trained with full precision gradients. The algorithm, which we call SpikeGrad, is based on accumulation and comparison operations and can naturally exploit sparsity in the gradient computation, which makes it an interesting choice for a spiking neuromorphic systems with on-chip learning capacities. |
| Tasks | |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00851v1 |
| https://arxiv.org/pdf/1906.00851v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600851 |
| Repo | |
| Framework | |
Tractography and machine learning: Current state and open challenges
| Title | Tractography and machine learning: Current state and open challenges |
| Authors | Philippe Poulin, Daniel Jörgens, Pierre-Marc Jodoin, Maxime Descoteaux |
| Abstract | Supervised machine learning (ML) algorithms have recently been proposed as an alternative to traditional tractography methods in order to address some of their weaknesses. They can be path-based and local-model-free, and easily incorporate anatomical priors to make contextual and non-local decisions that should help the tracking process. ML-based techniques have thus shown promising reconstructions of larger spatial extent of existing white matter bundles, promising reconstructions of less false positives, and promising robustness to known position and shape biases of current tractography techniques. But as of today, none of these ML-based methods have shown conclusive performances or have been adopted as a de facto solution to tractography. One reason for this might be the lack of well-defined and extensive frameworks to train, evaluate, and compare these methods. In this paper, we describe several datasets and evaluation tools that contain useful features for ML algorithms, along with the various methods proposed in the recent years. We then discuss the strategies that are used to evaluate and compare those methods, as well as their shortcomings. Finally, we describe the particular needs of ML tractography methods and discuss tangible solutions for future works. |
| Tasks | |
| Published | 2019-02-14 |
| URL | http://arxiv.org/abs/1902.05568v1 |
| http://arxiv.org/pdf/1902.05568v1.pdf | |
| PWC | https://paperswithcode.com/paper/tractography-and-machine-learning-current |
| Repo | |
| Framework | |
Medication Regimen Extraction From Medical Conversations
| Title | Medication Regimen Extraction From Medical Conversations |
| Authors | Sai P. Selvaraj, Sandeep Konam |
| Abstract | Extracting relevant information from medical conversations and providing it to doctors and patients might help in addressing doctor burnout and patient forgetfulness. In this paper, we focus on extracting the Medication Regimen (dosage and frequency for medications) discussed in a medical conversation. We frame the problem as a Question Answering (QA) task and perform comparative analysis over: a QA approach, a new combined QA and Information Extraction approach, and other baselines. We use a small corpus of 6,692 annotated doctor-patient conversations for the task. Clinical conversation corpora are costly to create, difficult to handle (because of data privacy concerns), and thus scarce. We address this data scarcity challenge through data augmentation methods, using publicly available embeddings and pretrain part of the network on a related task (summarization) to improve the model’s performance. Compared to the baseline, our best-performing models improve the dosage and frequency extractions’ ROUGE-1 F1 scores from 54.28 and 37.13 to 89.57 and 45.94, respectively. Using our best-performing model, we present the first fully automated system that can extract Medication Regimen tags from spontaneous doctor-patient conversations with about ~71% accuracy. |
| Tasks | Data Augmentation, Question Answering |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04961v2 |
| https://arxiv.org/pdf/1912.04961v2.pdf | |
| PWC | https://paperswithcode.com/paper/medication-regimen-extraction-from-clinical |
| Repo | |
| Framework | |
An Automated Vehicle (AV) like Me? The Impact of Personality Similarities and Differences between Humans and AVs
| Title | An Automated Vehicle (AV) like Me? The Impact of Personality Similarities and Differences between Humans and AVs |
| Authors | Qiaoning Zhang, Connor Esterwood, X. Jessie Yang, Lionel P. Robert Jr |
| Abstract | To better understand the impacts of similarities and dissimilarities in human and AV personalities we conducted an experimental study with 443 individuals. Generally, similarities in human and AV personalities led to a higher perception of AV safety only when both were high in specific personality traits. Dissimilarities in human and AV personalities also yielded a higher perception of AV safety, but only when the AV was higher than the human in a particular personality trait. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.11766v1 |
| https://arxiv.org/pdf/1909.11766v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-automated-vehicle-av-like-me-the-impact-of |
| Repo | |
| Framework | |
Constrained low-tubal-rank tensor recovery for hyperspectral images mixed noise removal by bilateral random projections
| Title | Constrained low-tubal-rank tensor recovery for hyperspectral images mixed noise removal by bilateral random projections |
| Authors | Hao Zhang, Xi-Le Zhao, Tai-Xiang Jiang, Michael Kwok-Po Ng |
| Abstract | In this paper, we propose a novel low-tubal-rank tensor recovery model, which directly constrains the tubal rank prior for effectively removing the mixed Gaussian and sparse noise in hyperspectral images. The constraints of tubal-rank and sparsity can govern the solution of the denoised tensor in the recovery procedure. To solve the constrained low-tubal-rank model, we develop an iterative algorithm based on bilateral random projections to efficiently solve the proposed model. The advantage of random projections is that the approximation of the low-tubal-rank tensor can be obtained quite accurately in an inexpensive manner. Experimental examples for hyperspectral image denoising are presented to demonstrate the effectiveness and efficiency of the proposed method. |
| Tasks | Denoising, Image Denoising |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.05941v1 |
| https://arxiv.org/pdf/1905.05941v1.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-low-tubal-rank-tensor-recovery |
| Repo | |
| Framework | |
Understanding Optical Music Recognition
| Title | Understanding Optical Music Recognition |
| Authors | Jorge Calvo-Zaragoza, Jan Hajič Jr., Alexander Pacha |
| Abstract | For over 50 years, researchers have been trying to teach computers to read music notation, referred to as Optical Music Recognition (OMR). However, this field is still difficult to access for new researchers, especially those without a significant musical background: few introductory materials are available, and furthermore the field has struggled with defining itself and building a shared terminology. In this tutorial, we address these shortcomings by (1) providing a robust definition of OMR and its relationship to related fields, (2) analyzing how OMR inverts the music encoding process to recover the musical notation and the musical semantics from documents, (3) proposing a taxonomy of OMR, with most notably a novel taxonomy of applications. Additionally, we discuss how deep learning affects modern OMR research, as opposed to the traditional pipeline. Based on this work, the reader should be able to attain a basic understanding of OMR: its objectives, its inherent structure, its relationship to other fields, the state of the art, and the research opportunities it affords. |
| Tasks | |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.03608v2 |
| https://arxiv.org/pdf/1908.03608v2.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-optical-music-recognition |
| Repo | |
| Framework | |
Query-based Interactive Recommendation by Meta-Path and Adapted Attention-GRU
| Title | Query-based Interactive Recommendation by Meta-Path and Adapted Attention-GRU |
| Authors | Yu Zhu, Yu Gong, Qingwen Liu, Yingcai Ma, Wenwu Ou, Junxiong Zhu, Beidou Wang, Ziyu Guan, Deng Cai |
| Abstract | Recently, interactive recommender systems are becoming increasingly popular. The insight is that, with the interaction between users and the system, (1) users can actively intervene the recommendation results rather than passively receive them, and (2) the system learns more about users so as to provide better recommendation. We focus on the single-round interaction, i.e. the system asks the user a question (Step 1), and exploits his feedback to generate better recommendation (Step 2). A novel query-based interactive recommender system is proposed in this paper, where \textbf{personalized questions are accurately generated from millions of automatically constructed questions} in Step 1, and \textbf{the recommendation is ensured to be closely-related to users’ feedback} in Step 2. We achieve this by transforming Step 1 into a query recommendation task and Step 2 into a retrieval task. The former task is our key challenge. We firstly propose a model based on Meta-Path to efficiently retrieve hundreds of query candidates from the large query pool. Then an adapted Attention-GRU model is developed to effectively rank these candidates for recommendation. Offline and online experiments on Taobao, a large-scale e-commerce platform in China, verify the effectiveness of our interactive system. The system has already gone into production in the homepage of Taobao App since Nov. 11, 2018 (see https://v.qq.com/x/page/s0833tkp1uo.html on how it works online). Our code and dataset are public in https://github.com/zyody/QueryQR. |
| Tasks | Recommendation Systems |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1907.01639v1 |
| https://arxiv.org/pdf/1907.01639v1.pdf | |
| PWC | https://paperswithcode.com/paper/query-based-interactive-recommendation-by |
| Repo | |
| Framework | |
Analysis of Word Embeddings using Fuzzy Clustering
| Title | Analysis of Word Embeddings using Fuzzy Clustering |
| Authors | Shahin Atakishiyev, Marek Z. Reformat |
| Abstract | In data dominated systems and applications, a concept of representing words in a numerical format has gained a lot of attention. There are a few approaches used to generate such a representation. An interesting issue that should be considered is the ability of such representations - called embeddings - to imitate human-based semantic similarity between words. In this study, we perform a fuzzy-based analysis of vector representations of words, i.e., word embeddings. We use two popular fuzzy clustering algorithms on count-based word embeddings, known as GloVe, of different dimensionality. Words from WordSim-353, called the gold standard, are represented as vectors and clustered. The results indicate that fuzzy clustering algorithms are very sensitive to high-dimensional data, and parameter tuning can dramatically change their performance. We show that by adjusting the value of the fuzzifier parameter, fuzzy clustering can be successfully applied to vectors of high - up to one hundred - dimensions. Additionally, we illustrate that fuzzy clustering allows to provide interesting results regarding membership of words to different clusters. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07672v2 |
| https://arxiv.org/pdf/1907.07672v2.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-word-embeddings-using-fuzzy |
| Repo | |
| Framework | |
Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data
| Title | Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data |
| Authors | Wei Ye, Bo Li, Rui Xie, Zhonghao Sheng, Long Chen, Shikun Zhang |
| Abstract | In practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class. However, the number of non-relation entity pairs in context (negative instances) usually far exceeds the others (positive instances), which negatively affects a model’s performance. To mitigate this problem, we propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss. Meanwhile, we observe that a sentence may have multiple entities and relation mentions, and the patterns in which the entities appear in a sentence may contain useful semantic information that can be utilized to distinguish between positive and negative instances. Thus we further incorporate the embeddings of character-wise/word-wise BIO tag from the named entity recognition task into character/word embeddings to enrich the input representation. Experiment results show that our proposed approach can significantly improve the performance of a baseline model with more than 10% absolute increase in F1-score, and outperform the state-of-the-art models on ACE 2005 Chinese and English corpus. Moreover, BIO tag embeddings are particularly effective and can be used to improve other models as well. |
| Tasks | Multi-Task Learning, Named Entity Recognition, Relation Classification, Relation Extraction, Word Embeddings |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.08931v1 |
| https://arxiv.org/pdf/1906.08931v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-entity-bio-tag-embeddings-and |
| Repo | |
| Framework | |
Developing an ANFIS PSO Model to Estimate Mercury Emission in Combustion Flue Gases
| Title | Developing an ANFIS PSO Model to Estimate Mercury Emission in Combustion Flue Gases |
| Authors | Shahaboddin Shamshirband, Masoud Hadipoor, Alireza Baghban, Amir Mosavi, Jozsef Bukor, Annamaria Varkonyi Koczy |
| Abstract | Accurate prediction of mercury content emitted from fossil fueled power stations is of utmost important for environmental pollution assessment and hazard mitigation. In this paper, mercury content in the output gas of power stations boilers was predicted using adaptive neuro fuzzy inference system method integrated with particle swarm optimization. The input parameters of the model include coal characteristics and the operational parameters of the boilers. The dataset has been collected from a number of power plants and employed to educate and examine the proposed model. To evaluate the performance of the proposed ANFIS PSO model the statistical meter of MARE was implemented. Furthermore, relative errors between acquired data and predicted values presented, which confirm the accuracy of the model to deal nonlinearity and representing the dependency of flue gas mercury content into the specifications of coal and the boiler type. |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1910.05118v1 |
| https://arxiv.org/pdf/1910.05118v1.pdf | |
| PWC | https://paperswithcode.com/paper/developing-an-anfis-pso-model-to-estimate |
| Repo | |
| Framework | |
