May 5, 2019

2835 words 14 mins read

Paper Group ANR 550

Learning to Rank Scientific Documents from the Crowd. Efficient Multiple Incremental Computation for Kernel Ridge Regression with Bayesian Uncertainty Modeling. Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation. What makes ImageNet good for transfer learning?. Note on the equivalence of hierarchical variational models and auxili …

Learning to Rank Scientific Documents from the Crowd


Title	Learning to Rank Scientific Documents from the Crowd
Authors	Jesse M Lingeman, Hong Yu
Abstract	Finding related published articles is an important task in any science, but with the explosion of new work in the biomedical domain it has become especially challenging. Most existing methodologies use text similarity metrics to identify whether two articles are related or not. However biomedical knowledge discovery is hypothesis-driven. The most related articles may not be ones with the highest text similarities. In this study, we first develop an innovative crowd-sourcing approach to build an expert-annotated document-ranking corpus. Using this corpus as the gold standard, we then evaluate the approaches of using text similarity to rank the relatedness of articles. Finally, we develop and evaluate a new supervised model to automatically rank related scientific articles. Our results show that authors’ ranking differ significantly from rankings by text-similarity-based models. By training a learning-to-rank model on a subset of the annotated corpus, we found the best supervised learning-to-rank model (SVM-Rank) significantly surpassed state-of-the-art baseline systems.
Tasks	Document Ranking, Learning-To-Rank
Published	2016-11-04
URL	http://arxiv.org/abs/1611.01400v1
PDF	http://arxiv.org/pdf/1611.01400v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-rank-scientific-documents-from
Repo
Framework

Efficient Multiple Incremental Computation for Kernel Ridge Regression with Bayesian Uncertainty Modeling


Title	Efficient Multiple Incremental Computation for Kernel Ridge Regression with Bayesian Uncertainty Modeling
Authors	Bo-Wei Chen, Nik Nailah Binti Abdullah, Sangoh Park
Abstract	This study presents an efficient incremental/decremental approach for big streams based on Kernel Ridge Regression (KRR), a frequently used data analysis in cloud centers. To avoid reanalyzing the whole dataset whenever sensors receive new training data, typical incremental KRR used a single-instance mechanism for updating an existing system. However, this inevitably increased redundant computational time, not to mention applicability to big streams. To this end, the proposed mechanism supports incremental/decremental processing for both single and multiple samples (i.e., batch processing). A large scale of data can be divided into batches, processed by a machine, without sacrificing the accuracy. Moreover, incremental/decremental analyses in empirical and intrinsic space are also proposed in this study to handle different types of data either with a large number of samples or high feature dimensions, whereas typical methods focused only on one type. At the end of this study, we further the proposed mechanism to statistical Kernelized Bayesian Regression, so that uncertainty modeling with incremental/decremental computation becomes applicable. Experimental results showed that computational time was significantly reduced, better than the original nonincremental design and the typical single incremental method. Furthermore, the accuracy of the proposed method remained the same as the baselines. This implied that the system enhanced efficiency without sacrificing the accuracy. These findings proved that the proposed method was appropriate for variable streaming data analysis, thereby demonstrating the effectiveness of the proposed method.
Tasks
Published	2016-08-01
URL	http://arxiv.org/abs/1608.00621v3
PDF	http://arxiv.org/pdf/1608.00621v3.pdf
PWC	https://paperswithcode.com/paper/efficient-multiple-incremental-computation
Repo
Framework

Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation


Title	Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation
Authors	Alberto P. García-Plaza, Víctor Fresno, Raquel Martínez, Arkaitz Zubiaga
Abstract	The selection of a suitable document representation approach plays a crucial role in the performance of a document clustering task. Being able to pick out representative words within a document can lead to substantial improvements in document clustering. In the case of web documents, the HTML markup that defines the layout of the content provides additional structural information that can be further exploited to identify representative words. In this paper we introduce a fuzzy term weighing approach that makes the most of the HTML structure for document clustering. We set forth and build on the hypothesis that a good representation can take advantage of how humans skim through documents to extract the most representative words. The authors of web pages make use of HTML tags to convey the most important message of a web page through page elements that attract the readers’ attention, such as page titles or emphasized elements. We define a set of criteria to exploit the information provided by these page elements, and introduce a fuzzy combination of these criteria that we evaluate within the context of a web page clustering task. Our proposed approach, called Abstract Fuzzy Combination of Criteria (AFCC), can adapt to datasets whose features are distributed differently, achieving good results compared to other similar fuzzy logic based approaches and TF-IDF across different datasets.
Tasks
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04429v1
PDF	http://arxiv.org/pdf/1606.04429v1.pdf
PWC	https://paperswithcode.com/paper/using-fuzzy-logic-to-leverage-html-markup-for
Repo
Framework

What makes ImageNet good for transfer learning?


Title	What makes ImageNet good for transfer learning?
Authors	Minyoung Huh, Pulkit Agrawal, Alexei A. Efros
Abstract	The tremendous success of ImageNet-trained deep features on a wide range of transfer tasks begs the question: what are the properties of the ImageNet dataset that are critical for learning good, general-purpose features? This work provides an empirical investigation of various facets of this question: Is more pre-training data always better? How does feature quality depend on the number of training examples per class? Does adding more object classes improve performance? For the same data budget, how should the data be split into classes? Is fine-grained recognition necessary for learning good features? Given the same number of training classes, is it better to have coarse classes or fine-grained classes? Which is better: more classes or more examples per class? To answer these and related questions, we pre-trained CNN features on various subsets of the ImageNet dataset and evaluated transfer performance on PASCAL detection, PASCAL action classification, and SUN scene classification tasks. Our overall findings suggest that most changes in the choice of pre-training data long thought to be critical do not significantly affect transfer performance.? Given the same number of training classes, is it better to have coarse classes or fine-grained classes? Which is better: more classes or more examples per class?
Tasks	Action Classification, Scene Classification, Transfer Learning
Published	2016-08-30
URL	http://arxiv.org/abs/1608.08614v2
PDF	http://arxiv.org/pdf/1608.08614v2.pdf
PWC	https://paperswithcode.com/paper/what-makes-imagenet-good-for-transfer
Repo
Framework

Note on the equivalence of hierarchical variational models and auxiliary deep generative models


Title	Note on the equivalence of hierarchical variational models and auxiliary deep generative models
Authors	Niko Brümmer
Abstract	This note compares two recently published machine learning methods for constructing flexible, but tractable families of variational hidden-variable posteriors. The first method, called “hierarchical variational models” enriches the inference model with an extra variable, while the other, called “auxiliary deep generative models”, enriches the generative model instead. We conclude that the two methods are mathematically equivalent.
Tasks
Published	2016-03-08
URL	http://arxiv.org/abs/1603.02443v2
PDF	http://arxiv.org/pdf/1603.02443v2.pdf
PWC	https://paperswithcode.com/paper/note-on-the-equivalence-of-hierarchical
Repo
Framework

Vector Quantization for Machine Vision


Title	Vector Quantization for Machine Vision
Authors	Vincenzo Liguori
Abstract	This paper shows how to reduce the computational cost for a variety of common machine vision tasks by operating directly in the compressed domain, particularly in the context of hardware acceleration. Pyramid Vector Quantization (PVQ) is the compression technique of choice and its properties are exploited to simplify Support Vector Machines (SVM), Convolutional Neural Networks(CNNs), Histogram of Oriented Gradients (HOG) features, interest points matching and other algorithms.
Tasks	Quantization
Published	2016-03-30
URL	http://arxiv.org/abs/1603.09037v1
PDF	http://arxiv.org/pdf/1603.09037v1.pdf
PWC	https://paperswithcode.com/paper/vector-quantization-for-machine-vision
Repo
Framework

Vocabulary Manipulation for Neural Machine Translation


Title	Vocabulary Manipulation for Neural Machine Translation
Authors	Haitao Mi, Zhiguo Wang, Abe Ittycheriah
Abstract	In order to capture rich language phenomena, neural machine translation models have to use a large vocabulary size, which requires high computing time and large memory usage. In this paper, we alleviate this issue by introducing a sentence-level or batch-level vocabulary, which is only a very small sub-set of the full output vocabulary. For each sentence or batch, we only predict the target words in its sentence-level or batch-level vocabulary. Thus, we reduce both the computing time and the memory usage. Our method simply takes into account the translation options of each word or phrase in the source sentence, and picks a very small target vocabulary for each sentence based on a word-to-word translation model or a bilingual phrase library learned from a traditional machine translation model. Experimental results on the large-scale English-to-French task show that our method achieves better translation performance by 1 BLEU point over the large vocabulary neural machine translation system of Jean et al. (2015).
Tasks	Machine Translation
Published	2016-05-10
URL	http://arxiv.org/abs/1605.03209v1
PDF	http://arxiv.org/pdf/1605.03209v1.pdf
PWC	https://paperswithcode.com/paper/vocabulary-manipulation-for-neural-machine
Repo
Framework

Deep Learning Markov Random Field for Semantic Segmentation


Title	Deep Learning Markov Random Field for Semantic Segmentation
Authors	Ziwei Liu, Xiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang
Abstract	Semantic segmentation tasks can be well modeled by Markov Random Field (MRF). This paper addresses semantic segmentation by incorporating high-order relations and mixture of label contexts into MRF. Unlike previous works that optimized MRFs using iterative algorithm, we solve MRF by proposing a Convolutional Neural Network (CNN), namely Deep Parsing Network (DPN), which enables deterministic end-to-end computation in a single forward pass. Specifically, DPN extends a contemporary CNN to model unary terms and additional layers are devised to approximate the mean field (MF) algorithm for pairwise terms. It has several appealing properties. First, different from the recent works that required many iterations of MF during back-propagation, DPN is able to achieve high performance by approximating one iteration of MF. Second, DPN represents various types of pairwise terms, making many existing models as its special cases. Furthermore, pairwise terms in DPN provide a unified framework to encode rich contextual information in high-dimensional data, such as images and videos. Third, DPN makes MF easier to be parallelized and speeded up, thus enabling efficient inference. DPN is thoroughly evaluated on standard semantic image/video segmentation benchmarks, where a single DPN model yields state-of-the-art segmentation accuracies on PASCAL VOC 2012, Cityscapes dataset and CamVid dataset.
Tasks	Semantic Segmentation, Video Semantic Segmentation
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07230v2
PDF	http://arxiv.org/pdf/1606.07230v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-markov-random-field-for
Repo
Framework

A Novel Progressive Learning Technique for Multi-class Classification


Title	A Novel Progressive Learning Technique for Multi-class Classification
Authors	Rajasekar Venkatesan, Meng Joo Er
Abstract	In this paper, a progressive learning technique for multi-class classification is proposed. This newly developed learning technique is independent of the number of class constraints and it can learn new classes while still retaining the knowledge of previous classes. Whenever a new class (non-native to the knowledge learnt thus far) is encountered, the neural network structure gets remodeled automatically by facilitating new neurons and interconnections, and the parameters are calculated in such a way that it retains the knowledge learnt thus far. This technique is suitable for real-world applications where the number of classes is often unknown and online learning from real-time data is required. The consistency and the complexity of the progressive learning technique are analyzed. Several standard datasets are used to evaluate the performance of the developed technique. A comparative study shows that the developed technique is superior.
Tasks
Published	2016-09-01
URL	http://arxiv.org/abs/1609.00085v2
PDF	http://arxiv.org/pdf/1609.00085v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-progressive-learning-technique-for
Repo
Framework

UTD-CRSS Systems for 2016 NIST Speaker Recognition Evaluation


Title	UTD-CRSS Systems for 2016 NIST Speaker Recognition Evaluation
Authors	Chunlei Zhang, Fahimeh Bahmaninezhad, Shivesh Ranjan, Chengzhu Yu, Navid Shokouhi, John H. L. Hansen
Abstract	This document briefly describes the systems submitted by the Center for Robust Speech Systems (CRSS) from The University of Texas at Dallas (UTD) to the 2016 National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation (SRE). We developed several UBM and DNN i-Vector based speaker recognition systems with different data sets and feature representations. Given that the emphasis of the NIST SRE 2016 is on language mismatch between training and enrollment/test data, so-called domain mismatch, in our system development we focused on: (1) using unlabeled in-domain data for centralizing data to alleviate the domain mismatch problem, (2) finding the best data set for training LDA/PLDA, (3) using newly proposed dimension reduction technique incorporating unlabeled in-domain data before PLDA training, (4) unsupervised speaker clustering of unlabeled data and using them alone or with previous SREs for PLDA training, (5) score calibration using only unlabeled data and combination of unlabeled and development (Dev) data as separate experiments.
Tasks	Calibration, Dimensionality Reduction, Speaker Recognition
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07651v1
PDF	http://arxiv.org/pdf/1610.07651v1.pdf
PWC	https://paperswithcode.com/paper/utd-crss-systems-for-2016-nist-speaker
Repo
Framework

Improving Vertebra Segmentation through Joint Vertebra-Rib Atlases


Title	Improving Vertebra Segmentation through Joint Vertebra-Rib Atlases
Authors	Yinong Wang, Jianhua Yao, Holger R. Roth, Joseph E. Burns, Ronald M. Summers
Abstract	Accurate spine segmentation allows for improved identification and quantitative characterization of abnormalities of the vertebra, such as vertebral fractures. However, in existing automated vertebra segmentation methods on computed tomography (CT) images, leakage into nearby bones such as ribs occurs due to the close proximity of these visibly intense structures in a 3D CT volume. To reduce this error, we propose the use of joint vertebra-rib atlases to improve the segmentation of vertebrae via multi-atlas joint label fusion. Segmentation was performed and evaluated on CTs containing 106 thoracic and lumbar vertebrae from 10 pathological and traumatic spine patients on an individual vertebra level basis. Vertebra atlases produced errors where the segmentation leaked into the ribs. The use of joint vertebra-rib atlases produced a statistically significant increase in the Dice coefficient from 92.5 $\pm$ 3.1% to 93.8 $\pm$ 2.1% for the left and right transverse processes and a decrease in the mean and max surface distance from 0.75 $\pm$ 0.60mm and 8.63 $\pm$ 4.44mm to 0.30 $\pm$ 0.27mm and 3.65 $\pm$ 2.87mm, respectively.
Tasks	Computed Tomography (CT)
Published	2016-02-01
URL	http://arxiv.org/abs/1602.00585v1
PDF	http://arxiv.org/pdf/1602.00585v1.pdf
PWC	https://paperswithcode.com/paper/improving-vertebra-segmentation-through-joint
Repo
Framework

Non-Deterministic Policy Improvement Stabilizes Approximated Reinforcement Learning


Title	Non-Deterministic Policy Improvement Stabilizes Approximated Reinforcement Learning
Authors	Wendelin Böhmer, Rong Guo, Klaus Obermayer
Abstract	This paper investigates a type of instability that is linked to the greedy policy improvement in approximated reinforcement learning. We show empirically that non-deterministic policy improvement can stabilize methods like LSPI by controlling the improvements’ stochasticity. Additionally we show that a suitable representation of the value function also stabilizes the solution to some degree. The presented approach is simple and should also be easily transferable to more sophisticated algorithms like deep reinforcement learning.
Tasks
Published	2016-12-22
URL	http://arxiv.org/abs/1612.07548v1
PDF	http://arxiv.org/pdf/1612.07548v1.pdf
PWC	https://paperswithcode.com/paper/non-deterministic-policy-improvement
Repo
Framework

Kernel regression, minimax rates and effective dimensionality: beyond the regular case


Title	Kernel regression, minimax rates and effective dimensionality: beyond the regular case
Authors	Gilles Blanchard, Nicole Mücke
Abstract	We investigate if kernel regularization methods can achieve minimax convergence rates over a source condition regularity assumption for the target function. These questions have been considered in past literature, but only under specific assumptions about the decay, typically polynomial, of the spectrum of the the kernel mapping covariance operator. In the perspective of distribution-free results, we investigate this issue under much weaker assumption on the eigenvalue decay, allowing for more complex behavior that can reflect different structure of the data at different scales.
Tasks
Published	2016-11-12
URL	http://arxiv.org/abs/1611.03979v1
PDF	http://arxiv.org/pdf/1611.03979v1.pdf
PWC	https://paperswithcode.com/paper/kernel-regression-minimax-rates-and-effective
Repo
Framework

Novelty Detection in MultiClass Scenarios with Incomplete Set of Class Labels


Title	Novelty Detection in MultiClass Scenarios with Incomplete Set of Class Labels
Authors	Nomi Vinokurov, Daphna Weinshall
Abstract	We address the problem of novelty detection in multiclass scenarios where some class labels are missing from the training set. Our method is based on the initial assignment of confidence values, which measure the affinity between a new test point and each known class. We first compare the values of the two top elements in this vector of confidence values. In the heart of our method lies the training of an ensemble of classifiers, each trained to discriminate known from novel classes based on some partition of the training data into presumed-known and presumednovel classes. Our final novelty score is derived from the output of this ensemble of classifiers. We evaluated our method on two datasets of images containing a relatively large number of classes - the Caltech-256 and Cifar-100 datasets. We compared our method to 3 alternative methods which represent commonly used approaches, including the one-class SVM, novelty based on k-NN, novelty based on maximal confidence, and the recent KNFST method. The results show a very clear and marked advantage for our method over all alternative methods, in an experimental setup where class labels are missing during training.
Tasks
Published	2016-04-21
URL	http://arxiv.org/abs/1604.06242v2
PDF	http://arxiv.org/pdf/1604.06242v2.pdf
PWC	https://paperswithcode.com/paper/novelty-detection-in-multiclass-scenarios
Repo
Framework

Multiple protein feature prediction with statistical relational learning


Title	Multiple protein feature prediction with statistical relational learning
Authors	Luca Masera
Abstract	High throughput sequencing techniques have highly impactedon modern biology, widening the gap between sequenced andannotated data. Automatic annotation tools are thereforeof the foremost importance to guide biologists’ experiments. However, most of the state-of-the-art methods rely on annotation transfer, offering reliable predictions only in homology settings. In this work we present a novel appraoch to protein feature prediction, which exploits the Semanti Based Regularization to inject prior knowledge in the learning process. The experimental results conducted on the yeast genome show that the introduction of the constraints positively impacts on the overall prediction quality.
Tasks	Relational Reasoning
Published	2016-09-27
URL	http://arxiv.org/abs/1609.08391v1
PDF	http://arxiv.org/pdf/1609.08391v1.pdf
PWC	https://paperswithcode.com/paper/multiple-protein-feature-prediction-with
Repo
Framework