July 28, 2019

2913 words 14 mins read

Paper Group ANR 456

A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models. Adaptive SVM+: Learning with Privileged Information for Domain Adaptation. Clustering in Hilbert simplex geometry. Detection of Tooth caries in Bitewing Radiographs using Deep Learning. FoodNet: Recognizing Foods Using Ensemble of Deep Networks. Pattern Recogn …

A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models


Title	A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models
Authors	Kartik Goyal, Graham Neubig, Chris Dyer, Taylor Berg-Kirkpatrick
Abstract	Beam search is a desirable choice of test-time decoding algorithm for neural sequence models because it potentially avoids search errors made by simpler greedy methods. However, typical cross entropy training procedures for these models do not directly consider the behaviour of the final decoding method. As a result, for cross-entropy trained models, beam decoding can sometimes yield reduced test performance when compared with greedy decoding. In order to train models that can more effectively make use of beam search, we propose a new training procedure that focuses on the final loss metric (e.g. Hamming loss) evaluated on the output of beam search. While well-defined, this “direct loss” objective is itself discontinuous and thus difficult to optimize. Hence, in our approach, we form a sub-differentiable surrogate objective by introducing a novel continuous approximation of the beam search decoding procedure. In experiments, we show that optimizing this new training objective yields substantially better results on two sequence tasks (Named Entity Recognition and CCG Supertagging) when compared with both cross entropy trained greedy decoding and cross entropy trained beam decoding baselines.
Tasks	CCG Supertagging, Motion Segmentation, Named Entity Recognition
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00111v2
PDF	http://arxiv.org/pdf/1708.00111v2.pdf
PWC	https://paperswithcode.com/paper/a-continuous-relaxation-of-beam-search-for
Repo
Framework

Adaptive SVM+: Learning with Privileged Information for Domain Adaptation


Title	Adaptive SVM+: Learning with Privileged Information for Domain Adaptation
Authors	Nikolaos Sarafianos, Michalis Vrigkas, Ioannis A. Kakadiaris
Abstract	Incorporating additional knowledge in the learning process can be beneficial for several computer vision and machine learning tasks. Whether privileged information originates from a source domain that is adapted to a target domain, or as additional features available at training time only, using such privileged (i.e., auxiliary) information is of high importance as it improves the recognition performance and generalization. However, both primary and privileged information are rarely derived from the same distribution, which poses an additional challenge to the recognition task. To address these challenges, we present a novel learning paradigm that leverages privileged information in a domain adaptation setup to perform visual recognition tasks. The proposed framework, named Adaptive SVM+, combines the advantages of both the learning using privileged information (LUPI) paradigm and the domain adaptation framework, which are naturally embedded in the objective function of a regular SVM. We demonstrate the effectiveness of our approach on the publicly available Animals with Attributes and INTERACT datasets and report state-of-the-art results in both of them.
Tasks	Domain Adaptation
Published	2017-08-30
URL	http://arxiv.org/abs/1708.09083v1
PDF	http://arxiv.org/pdf/1708.09083v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-svm-learning-with-privileged
Repo
Framework

Clustering in Hilbert simplex geometry


Title	Clustering in Hilbert simplex geometry
Authors	Frank Nielsen, Ke Sun
Abstract	Clustering categorical distributions in the probability simplex is a fundamental task met in many applications dealing with normalized histograms. Traditionally, the differential-geometric structures of the probability simplex have been used either by (i) setting the Riemannian metric tensor to the Fisher information matrix of the categorical distributions, or (ii) defining the dualistic information-geometric structure induced by a smooth dissimilarity measure, the Kullback-Leibler divergence. In this work, we introduce for this clustering task a novel computationally-friendly framework for modeling the probability simplex termed {\em Hilbert simplex geometry}. In the Hilbert simplex geometry, the distance function is described by a polytope. We discuss the pros and cons of those different statistical modelings, and benchmark experimentally these geometries for center-based $k$-means and $k$-center clusterings. We show that Hilbert metric in the probability simplex satisfies the property of information monotonicity. Furthermore, since a canonical Hilbert metric distance can be defined on any bounded convex subset of the Euclidean space, we also consider Hilbert’s projective geometry of the elliptope of correlation matrices and study its clustering performances.
Tasks
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00454v5
PDF	http://arxiv.org/pdf/1704.00454v5.pdf
PWC	https://paperswithcode.com/paper/clustering-in-hilbert-simplex-geometry
Repo
Framework

Detection of Tooth caries in Bitewing Radiographs using Deep Learning


Title	Detection of Tooth caries in Bitewing Radiographs using Deep Learning
Authors	Muktabh Mayank Srivastava, Pratyush Kumar, Lalit Pradhan, Srikrishna Varadarajan
Abstract	We develop a Computer Aided Diagnosis (CAD) system, which enhances the performance of dentists in detecting wide range of dental caries. The CAD System achieves this by acting as a second opinion for the dentists with way higher sensitivity on the task of detecting cavities than the dentists themselves. We develop annotated dataset of more than 3000 bitewing radiographs and utilize it for developing a system for automated diagnosis of dental caries. Our system consists of a deep fully convolutional neural network (FCNN) consisting 100+ layers, which is trained to mark caries on bitewing radiographs. We have compared the performance of our proposed system with three certified dentists for marking dental caries. We exceed the average performance of the dentists in both recall (sensitivity) and F1-Score (agreement with truth) by a very large margin. Working example of our system is shown in Figure 1.
Tasks
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07312v2
PDF	http://arxiv.org/pdf/1711.07312v2.pdf
PWC	https://paperswithcode.com/paper/detection-of-tooth-caries-in-bitewing
Repo
Framework

FoodNet: Recognizing Foods Using Ensemble of Deep Networks


Title	FoodNet: Recognizing Foods Using Ensemble of Deep Networks
Authors	Paritosh Pandey, Akella Deepthi, Bappaditya Mandal, N. B. Puhan
Abstract	In this work we propose a methodology for an automatic food classification system which recognizes the contents of the meal from the images of the food. We developed a multi-layered deep convolutional neural network (CNN) architecture that takes advantages of the features from other deep networks and improves the efficiency. Numerous classical handcrafted features and approaches are explored, among which CNNs are chosen as the best performing features. Networks are trained and fine-tuned using preprocessed images and the filter outputs are fused to achieve higher accuracy. Experimental results on the largest real-world food recognition database ETH Food-101 and newly contributed Indian food image database demonstrate the effectiveness of the proposed methodology as compared to many other benchmark deep learned CNN frameworks.
Tasks	Food Recognition
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09429v1
PDF	http://arxiv.org/pdf/1709.09429v1.pdf
PWC	https://paperswithcode.com/paper/foodnet-recognizing-foods-using-ensemble-of
Repo
Framework

Pattern Recognition using Artificial Immune System


Title	Pattern Recognition using Artificial Immune System
Authors	Mohammad Tarek Al Muallim
Abstract	In this thesis, the uses of Artificial Immune Systems (AIS) in Machine learning is studded. the thesis focus on some of immune inspired algorithms such as clonal selection algorithm and artificial immune network. The effect of changing the algorithm parameter on its performance is studded. Then a new immune inspired algorithm for unsupervised classification is proposed. The new algorithm is based on clonal selection principle and named Unsupervised Clonal Selection Classification (UCSC). The new proposed algorithm is almost parameter free. The algorithm parameters are data driven and it adjusts itself to make the classification as fast as possible. The performance of UCSC is evaluated. The experiments show that the proposed UCSC algorithm has a good performance and more reliable.
Tasks
Published	2017-04-19
URL	http://arxiv.org/abs/1709.04317v1
PDF	http://arxiv.org/pdf/1709.04317v1.pdf
PWC	https://paperswithcode.com/paper/pattern-recognition-using-artificial-immune
Repo
Framework

Visual Question Answering with Memory-Augmented Networks


Title	Visual Question Answering with Memory-Augmented Networks
Authors	Chao Ma, Chunhua Shen, Anthony Dick, Qi Wu, Peng Wang, Anton van den Hengel, Ian Reid
Abstract	In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set. The memory network incorporates both internal and external memory blocks and selectively pays attention to each training exemplar. We show that memory-augmented neural networks are able to maintain a relatively long-term memory of scarce training exemplars, which is important for visual question answering due to the heavy-tailed distribution of answers in a general VQA setting. Experimental results on two large-scale benchmark datasets show the favorable performance of the proposed algorithm with a comparison to state of the art.
Tasks	Question Answering, Visual Question Answering
Published	2017-07-17
URL	http://arxiv.org/abs/1707.04968v2
PDF	http://arxiv.org/pdf/1707.04968v2.pdf
PWC	https://paperswithcode.com/paper/visual-question-answering-with-memory
Repo
Framework

Enabling Early Audio Event Detection with Neural Networks


Title	Enabling Early Audio Event Detection with Neural Networks
Authors	Huy Phan, Philipp Koch, Ian McLoughlin, Alfred Mertins
Abstract	This paper presents a methodology for early detection of audio events from audio streams. Early detection is the ability to infer an ongoing event during its initial stage. The proposed system consists of a novel inference step coupled with dual parallel tailored-loss deep neural networks (DNNs). The DNNs share a similar architecture except for their loss functions, i.e. weighted loss and multitask loss, which are designed to efficiently cope with issues common to audio event detection. The inference step is newly introduced to make use of the network outputs for recognizing ongoing events. The monotonicity of the detection function is required for reliable early detection, and will also be proved. Experiments on the ITC-Irst database show that the proposed system achieves state-of-the-art detection performance. Furthermore, even partial events are sufficient to achieve good performance similar to that obtained when an entire event is observed, enabling early event detection.
Tasks
Published	2017-12-06
URL	http://arxiv.org/abs/1712.02116v2
PDF	http://arxiv.org/pdf/1712.02116v2.pdf
PWC	https://paperswithcode.com/paper/enabling-early-audio-event-detection-with
Repo
Framework

Extracting Ontological Knowledge from Textual Descriptions


Title	Extracting Ontological Knowledge from Textual Descriptions
Authors	Kevin Alex Mathews, P Sreenivasa Kumar
Abstract	Authoring of OWL-DL ontologies is intellectually challenging and to make this process simpler, many systems accept natural language text as input. A text-based ontology authoring approach can be successful only when it is combined with an effective method for extracting ontological axioms from text. Extracting axioms from unrestricted English input is a substantially challenging task due to the richness of the language. Controlled natural languages (CNLs) have been proposed in this context and these tend to be highly restrictive. In this paper, we propose a new CNL called TEDEI (TExtual DEscription Identifier) whose grammar is inspired by the different ways OWL-DL constructs are expressed in English. We built a system that transforms TEDEI sentences into corresponding OWL-DL axioms. Now, ambiguity due to different possible lexicalizations of sentences and semantic ambiguity present in sentences are challenges in this context. We find that the best way to handle these challenges is to construct axioms corresponding to alternative formalizations of the sentence so that the end-user can make an appropriate choice. The output is compared against human-authored axioms and in substantial number of cases, human-authored axiom is indeed one of the alternatives given by the system. The proposed system substantially enhances the types of sentence structures that can be used for ontology authoring.
Tasks
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08448v3
PDF	http://arxiv.org/pdf/1709.08448v3.pdf
PWC	https://paperswithcode.com/paper/extracting-ontological-knowledge-from-textual
Repo
Framework

Source-Sensitive Belief Change


Title	Source-Sensitive Belief Change
Authors	Shahab Ebrahimi
Abstract	The AGM model is the most remarkable framework for modeling belief revision. However, it is not perfect in all aspects. Paraconsistent belief revision, multi-agent belief revision and non-prioritized belief revision are three different extensions to AGM to address three important criticisms applied to it. In this article, we propose a framework based on AGM that takes a position in each of these categories. Also, we discuss some features of our framework and study the satisfiability of AGM postulates in this new context.
Tasks
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03396v2
PDF	http://arxiv.org/pdf/1704.03396v2.pdf
PWC	https://paperswithcode.com/paper/source-sensitive-belief-change
Repo
Framework

Verifying Properties of Binarized Deep Neural Networks


Title	Verifying Properties of Binarized Deep Neural Networks
Authors	Nina Narodytska, Shiva Prasad Kasiviswanathan, Leonid Ryzhyk, Mooly Sagiv, Toby Walsh
Abstract	Understanding properties of deep neural networks is an important challenge in deep learning. In this paper, we take a step in this direction by proposing a rigorous way of verifying properties of a popular class of neural networks, Binarized Neural Networks, using the well-developed means of Boolean satisfiability. Our main contribution is a construction that creates a representation of a binarized neural network as a Boolean formula. Our encoding is the first exact Boolean representation of a deep neural network. Using this encoding, we leverage the power of modern SAT solvers along with a proposed counterexample-guided search procedure to verify various properties of these networks. A particular focus will be on the critical property of robustness to adversarial perturbations. For this property, our experimental results demonstrate that our approach scales to medium-size deep neural networks used in image classification tasks. To the best of our knowledge, this is the first work on verifying properties of deep neural networks using an exact Boolean encoding of the network.
Tasks	Image Classification
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06662v2
PDF	http://arxiv.org/pdf/1709.06662v2.pdf
PWC	https://paperswithcode.com/paper/verifying-properties-of-binarized-deep-neural
Repo
Framework

Predicting Abandonment in Online Coding Tutorials


Title	Predicting Abandonment in Online Coding Tutorials
Authors	An Yan, Michael J. Lee, Andrew J. Ko
Abstract	Learners regularly abandon online coding tutorials when they get bored or frustrated, but there are few techniques for anticipating this abandonment to intervene. In this paper, we examine the feasibility of predicting abandonment with machine-learned classifiers. Using interaction logs from an online programming game, we extracted a collection of features that are potentially related to learner abandonment and engagement, then developed classifiers for each level. Across the first five levels of the game, our classifiers successfully predicted 61% to 76% of learners who did not complete the next level, achieving an average AUC of 0.68. In these classifiers, features negatively associated with abandonment included account activation and help-seeking behaviors, whereas features positively associated with abandonment included features indicating difficulty and disengagement. These findings highlight the feasibility of providing timely intervention to learners likely to quit.
Tasks
Published	2017-07-13
URL	http://arxiv.org/abs/1707.04291v1
PDF	http://arxiv.org/pdf/1707.04291v1.pdf
PWC	https://paperswithcode.com/paper/predicting-abandonment-in-online-coding
Repo
Framework

The Pose Knows: Video Forecasting by Generating Pose Futures


Title	The Pose Knows: Video Forecasting by Generating Pose Futures
Authors	Jacob Walker, Kenneth Marino, Abhinav Gupta, Martial Hebert
Abstract	Current approaches in video forecasting attempt to generate videos directly in pixel space using Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). However, since these approaches try to model all the structure and scene dynamics at once, in unconstrained settings they often generate uninterpretable results. Our insight is to model the forecasting problem at a higher level of abstraction. Specifically, we exploit human pose detectors as a free source of supervision and break the video forecasting problem into two discrete steps. First we explicitly model the high level structure of active objects in the scene—humans—and use a VAE to model the possible future movements of humans in the pose space. We then use the future poses generated as conditional information to a GAN to predict the future frames of the video in pixel space. By using the structured space of pose as an intermediate representation, we sidestep the problems that GANs have in generating video pixels directly. We show through quantitative and qualitative evaluation that our method outperforms state-of-the-art methods for video prediction.
Tasks	Video Prediction
Published	2017-04-28
URL	http://arxiv.org/abs/1705.00053v1
PDF	http://arxiv.org/pdf/1705.00053v1.pdf
PWC	https://paperswithcode.com/paper/the-pose-knows-video-forecasting-by
Repo
Framework

Probabilistic Sensor Fusion for Ambient Assisted Living


Title	Probabilistic Sensor Fusion for Ambient Assisted Living
Authors	Tom Diethe, Niall Twomey, Meelis Kull, Peter Flach, Ian Craddock
Abstract	There is a widely-accepted need to revise current forms of health-care provision, with particular interest in sensing systems in the home. Given a multiple-modality sensor platform with heterogeneous network connectivity, as is under development in the Sensor Platform for HEalthcare in Residential Environment (SPHERE) Interdisciplinary Research Collaboration (IRC), we face specific challenges relating to the fusion of the heterogeneous sensor modalities. We introduce Bayesian models for sensor fusion, which aims to address the challenges of fusion of heterogeneous sensor modalities. Using this approach we are able to identify the modalities that have most utility for each particular activity, and simultaneously identify which features within that activity are most relevant for a given activity. We further show how the two separate tasks of location prediction and activity recognition can be fused into a single model, which allows for simultaneous learning an prediction for both tasks. We analyse the performance of this model on data collected in the SPHERE house, and show its utility. We also compare against some benchmark models which do not have the full structure,and show how the proposed model compares favourably to these methods
Tasks	Activity Recognition, Sensor Fusion
Published	2017-02-04
URL	http://arxiv.org/abs/1702.01209v1
PDF	http://arxiv.org/pdf/1702.01209v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-sensor-fusion-for-ambient
Repo
Framework

Large-Scale Low-Rank Matrix Learning with Nonconvex Regularizers


Title	Large-Scale Low-Rank Matrix Learning with Nonconvex Regularizers
Authors	Quanming Yao, James T. Kwok, Taifeng Wang, Tie-Yan Liu
Abstract	Low-rank modeling has many important applications in computer vision and machine learning. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has demonstrated better empirical performance. However, the resulting optimization problem is much more challenging. Recent state-of-the-art requires an expensive full SVD in each iteration. In this paper, we show that for many commonly-used nonconvex low-rank regularizers, a cutoff can be derived to automatically threshold the singular values obtained from the proximal operator. This allows such operator being efficiently approximated by power method. Based on it, we develop a proximal gradient algorithm (and its accelerated variant) with inexact proximal splitting and prove that a convergence rate of O(1/T) where T is the number of iterations is guaranteed. Furthermore, we show the proposed algorithm can be well parallelized, which achieves nearly linear speedup w.r.t the number of threads. Extensive experiments are performed on matrix completion and robust principal component analysis, which shows a significant speedup over the state-of-the-art. Moreover, the matrix solution obtained is more accurate and has a lower rank than that of the nuclear norm regularizer.
Tasks	Matrix Completion
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00146v3
PDF	http://arxiv.org/pdf/1708.00146v3.pdf
PWC	https://paperswithcode.com/paper/large-scale-low-rank-matrix-learning-with
Repo
Framework