July 29, 2019

2832 words 14 mins read

Paper Group ANR 129

Global and Local Information Based Deep Network for Skin Lesion Segmentation. Mahalanonbis Distance Informed by Clustering. A Neural Network model with Bidirectional Whitening. Automatic breast cancer grading in lymph nodes using a deep neural network. Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Langua …

Global and Local Information Based Deep Network for Skin Lesion Segmentation


Title	Global and Local Information Based Deep Network for Skin Lesion Segmentation
Authors	Jin Qi, Miao Le, Chunming Li, Ping Zhou
Abstract	With a large influx of dermoscopy images and a growing shortage of dermatologists, automatic dermoscopic image analysis plays an essential role in skin cancer diagnosis. In this paper, a new deep fully convolutional neural network (FCNN) is proposed to automatically segment melanoma out of skin images by end-to-end learning with only pixels and labels as inputs. Our proposed FCNN is capable of using both local and global information to segment melanoma by adopting skipping layers. The public benchmark database consisting of 150 validation images, 600 test images and 2000 training images in the melanoma detection challenge 2017 at International Symposium Biomedical Imaging 2017 is used to test the performance of our algorithm. All large size images (for example, $4000\times 6000$ pixels) are reduced to much smaller images with $384\times 384$ pixels (more than 10 times smaller). We got and submitted preliminary results to the challenge without any pre or post processing. The performance of our proposed method could be further improved by data augmentation and by avoiding image size reduction.
Tasks	Data Augmentation, Lesion Segmentation
Published	2017-03-16
URL	http://arxiv.org/abs/1703.05467v1
PDF	http://arxiv.org/pdf/1703.05467v1.pdf
PWC	https://paperswithcode.com/paper/global-and-local-information-based-deep
Repo
Framework

Mahalanonbis Distance Informed by Clustering


Title	Mahalanonbis Distance Informed by Clustering
Authors	Almog Lahav, Ronen Talmon, Yuval Kluger
Abstract	A fundamental question in data analysis, machine learning and signal processing is how to compare between data points. The choice of the distance metric is specifically challenging for high-dimensional data sets, where the problem of meaningfulness is more prominent (e.g. the Euclidean distance between images). In this paper, we propose to exploit a property of high-dimensional data that is usually ignored - which is the structure stemming from the relationships between the coordinates. Specifically we show that organizing similar coordinates in clusters can be exploited for the construction of the Mahalanobis distance between samples. When the observable samples are generated by a nonlinear transformation of hidden variables, the Mahalanobis distance allows the recovery of the Euclidean distances in the hidden space.We illustrate the advantage of our approach on a synthetic example where the discovery of clusters of correlated coordinates improves the estimation of the principal directions of the samples. Our method was applied to real data of gene expression for lung adenocarcinomas (lung cancer). By using the proposed metric we found a partition of subjects to risk groups with a good separation between their Kaplan-Meier survival plot.
Tasks
Published	2017-08-13
URL	http://arxiv.org/abs/1708.03914v1
PDF	http://arxiv.org/pdf/1708.03914v1.pdf
PWC	https://paperswithcode.com/paper/mahalanonbis-distance-informed-by-clustering
Repo
Framework

A Neural Network model with Bidirectional Whitening


Title	A Neural Network model with Bidirectional Whitening
Authors	Yuki Fujimoto, Toru Ohira
Abstract	We present here a new model and algorithm which performs an efficient Natural gradient descent for Multilayer Perceptrons. Natural gradient descent was originally proposed from a point of view of information geometry, and it performs the steepest descent updates on manifolds in a Riemannian space. In particular, we extend an approach taken by the “Whitened neural networks” model. We make the whitening process not only in feed-forward direction as in the original model, but also in the back-propagation phase. Its efficacy is shown by an application of this “Bidirectional whitened neural networks” model to a handwritten character recognition data (MNIST data).
Tasks
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07147v1
PDF	http://arxiv.org/pdf/1704.07147v1.pdf
PWC	https://paperswithcode.com/paper/a-neural-network-model-with-bidirectional
Repo
Framework

Automatic breast cancer grading in lymph nodes using a deep neural network


Title	Automatic breast cancer grading in lymph nodes using a deep neural network
Authors	Thomas Wollmann, Karl Rohr
Abstract	The progression of breast cancer can be quantified in lymph node whole-slide images (WSIs). We describe a novel method for effectively performing classification of whole-slide images and patient level breast cancer grading. Our method utilises a deep neural network. The method performs classification on small patches and uses model averaging for boosting. In the first step, region of interest patches are determined and cropped automatically by color thresholding and then classified by the deep neural network. The classification results are used to determine a slide level class and for further aggregation to predict a patient level grade. Fast processing speed of our method enables high throughput image analysis.
Tasks
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07565v1
PDF	http://arxiv.org/pdf/1707.07565v1.pdf
PWC	https://paperswithcode.com/paper/automatic-breast-cancer-grading-in-lymph
Repo
Framework

Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Language Data


Title	Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Language Data
Authors	Chia-Hao Shen, Janet Y. Sung, Hung-Yi Lee
Abstract	Audio Word2Vec offers vector representations of fixed dimensionality for variable-length audio segments using Sequence-to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the audio segments to a good degree, with real world applications such as query-by-example Spoken Term Detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the audio segments of another language (target language). We found that SA can still catch phonetic structure from the audio segments of the target language if the source and target languages are similar. In query-by-example STD, we obtain the vector representations from the SA learned from a large amount of source language data, and found them surpass the representations from naive encoder and SA directly learned from a small amount of target language data. The result shows that it is possible to learn Audio Word2Vec model from high-resource languages and use it on low-resource languages. This further expands the usability of Audio Word2Vec.
Tasks
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06519v1
PDF	http://arxiv.org/pdf/1707.06519v1.pdf
PWC	https://paperswithcode.com/paper/language-transfer-of-audio-word2vec-learning
Repo
Framework

Audio-Visual Sentiment Analysis for Learning Emotional Arcs in Movies


Title	Audio-Visual Sentiment Analysis for Learning Emotional Arcs in Movies
Authors	Eric Chu, Deb Roy
Abstract	Stories can have tremendous power – not only useful for entertainment, they can activate our interests and mobilize our actions. The degree to which a story resonates with its audience may be in part reflected in the emotional journey it takes the audience upon. In this paper, we use machine learning methods to construct emotional arcs in movies, calculate families of arcs, and demonstrate the ability for certain arcs to predict audience engagement. The system is applied to Hollywood films and high quality shorts found on the web. We begin by using deep convolutional neural networks for audio and visual sentiment analysis. These models are trained on both new and existing large-scale datasets, after which they can be used to compute separate audio and visual emotional arcs. We then crowdsource annotations for 30-second video clips extracted from highs and lows in the arcs in order to assess the micro-level precision of the system, with precision measured in terms of agreement in polarity between the system’s predictions and annotators’ ratings. These annotations are also used to combine the audio and visual predictions. Next, we look at macro-level characterizations of movies by investigating whether there exist `universal shapes’ of emotional arcs. In particular, we develop a clustering approach to discover distinct classes of emotional arcs. Finally, we show on a sample corpus of short web videos that certain emotional arcs are statistically significant predictors of the number of comments a video receives. These results suggest that the emotional arcs learned by our approach successfully represent macroscopic aspects of a video story that drive audience engagement. Such machine understanding could be used to predict audience reactions to video stories, ultimately improving our ability as storytellers to communicate with each other. \|
Tasks	Sentiment Analysis
Published	2017-12-08
URL	http://arxiv.org/abs/1712.02896v1
PDF	http://arxiv.org/pdf/1712.02896v1.pdf
PWC	https://paperswithcode.com/paper/audio-visual-sentiment-analysis-for-learning
Repo
Framework

Generative Adversarial Active Learning


Title	Generative Adversarial Active Learning
Authors	Jia-Jie Zhu, José Bento
Abstract	We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our idea can work with other active learning principles. We report results from various numerical experiments to demonstrate the effectiveness the proposed approach. In some settings, the proposed algorithm outperforms traditional pool-based approaches. To the best our knowledge, this is the first active learning work using GAN.
Tasks	Active Learning
Published	2017-02-25
URL	http://arxiv.org/abs/1702.07956v5
PDF	http://arxiv.org/pdf/1702.07956v5.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-active-learning
Repo
Framework

Investigating the Characteristics of One-Sided Matching Mechanisms Under Various Preferences and Risk Attitudes


Title	Investigating the Characteristics of One-Sided Matching Mechanisms Under Various Preferences and Risk Attitudes
Authors	Hadi Hosseini, Kate Larson, Robin Cohen
Abstract	One-sided matching mechanisms are fundamental for assigning a set of indivisible objects to a set of self-interested agents when monetary transfers are not allowed. Two widely-studied randomized mechanisms in multiagent settings are the Random Serial Dictatorship (RSD) and the Probabilistic Serial Rule (PS). Both mechanisms require only that agents specify ordinal preferences and have a number of desirable economic and computational properties. However, the induced outcomes of the mechanisms are often incomparable and thus there are challenges when it comes to deciding which mechanism to adopt in practice. In this paper, we first consider the space of general ordinal preferences and provide empirical results on the (in)comparability of RSD and PS. We analyze their respective economic properties under general and lexicographic preferences. We then instantiate utility functions with the goal of gaining insights on the manipulability, efficiency, and envyfreeness of the mechanisms under different risk-attitude models. Our results hold under various preference distribution models, which further confirm the broad use of RSD in most practical applications.
Tasks
Published	2017-03-01
URL	http://arxiv.org/abs/1703.00320v1
PDF	http://arxiv.org/pdf/1703.00320v1.pdf
PWC	https://paperswithcode.com/paper/investigating-the-characteristics-of-one
Repo
Framework

Representation-Aggregation Networks for Segmentation of Multi-Gigapixel Histology Images


Title	Representation-Aggregation Networks for Segmentation of Multi-Gigapixel Histology Images
Authors	Abhinav Agarwalla, Muhammad Shaban, Nasir M. Rajpoot
Abstract	Convolutional Neural Network (CNN) models have become the state-of-the-art for most computer vision tasks with natural images. However, these are not best suited for multi-gigapixel resolution Whole Slide Images (WSIs) of histology slides due to large size of these images. Current approaches construct smaller patches from WSIs which results in the loss of contextual information. We propose to capture the spatial context using novel Representation-Aggregation Network (RAN) for segmentation purposes, wherein the first network learns patch-level representation and the second network aggregates context from a grid of neighbouring patches. We can use any CNN for representation learning, and can utilize CNN or 2D-Long Short Term Memory (2D-LSTM) for context-aggregation. Our method significantly outperformed conventional patch-based CNN approaches on segmentation of tumour in WSIs of breast cancer tissue sections.
Tasks	Representation Learning
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08814v1
PDF	http://arxiv.org/pdf/1707.08814v1.pdf
PWC	https://paperswithcode.com/paper/representation-aggregation-networks-for
Repo
Framework

Novel Adaptive Genetic Algorithm Sample Consensus


Title	Novel Adaptive Genetic Algorithm Sample Consensus
Authors	Ehsan Shojaedini, Mahshid Majd, Reza Safabakhsh
Abstract	Random sample consensus (RANSAC) is a successful algorithm in model fitting applications. It is vital to have strong exploration phase when there are an enormous amount of outliers within the dataset. Achieving a proper model is guaranteed by pure exploration strategy of RANSAC. However, finding the optimum result requires exploitation. GASAC is an evolutionary paradigm to add exploitation capability to the algorithm. Although GASAC improves the results of RANSAC, it has a fixed strategy for balancing between exploration and exploitation. In this paper, a new paradigm is proposed based on genetic algorithm with an adaptive strategy. We utilize an adaptive genetic operator to select high fitness individuals as parents and mutate low fitness ones. In the mutation phase, a training method is used to gradually learn which gene is the best replacement for the mutated gene. The proposed method adaptively balance between exploration and exploitation by learning about genes. During the final Iterations, the algorithm draws on this information to improve the final results. The proposed method is extensively evaluated on two set of experiments. In all tests, our method outperformed the other methods in terms of both the number of inliers found and the speed of the algorithm.
Tasks
Published	2017-11-26
URL	http://arxiv.org/abs/1711.09398v1
PDF	http://arxiv.org/pdf/1711.09398v1.pdf
PWC	https://paperswithcode.com/paper/novel-adaptive-genetic-algorithm-sample
Repo
Framework

Variable selection for clustering with Gaussian mixture models: state of the art


Title	Variable selection for clustering with Gaussian mixture models: state of the art
Authors	Abdelghafour Talibi, Boujemâa Achchab, Rafik Lasri
Abstract	The mixture models have become widely used in clustering, given its probabilistic framework in which its based, however, for modern databases that are characterized by their large size, these models behave disappointingly in setting out the model, making essential the selection of relevant variables for this type of clustering. After recalling the basics of clustering based on a model, this article will examine the variable selection methods for model-based clustering, as well as presenting opportunities for improvement of these methods.
Tasks
Published	2017-01-31
URL	http://arxiv.org/abs/1701.08946v1
PDF	http://arxiv.org/pdf/1701.08946v1.pdf
PWC	https://paperswithcode.com/paper/variable-selection-for-clustering-with
Repo
Framework

Artificial Intelligence and Statistics


Title	Artificial Intelligence and Statistics
Authors	Bin Yu, Karl Kumbier
Abstract	Artificial intelligence (AI) is intrinsically data-driven. It calls for the application of statistical concepts through human-machine collaboration during generation of data, development of algorithms, and evaluation of results. This paper discusses how such human-machine collaboration can be approached through the statistical concepts of population, question of interest, representativeness of training data, and scrutiny of results (PQRS). The PQRS workflow provides a conceptual framework for integrating statistical ideas with human input into AI products and research. These ideas include experimental design principles of randomization and local control as well as the principle of stability to gain reproducibility and interpretability of algorithms and data results. We discuss the use of these principles in the contexts of self-driving cars, automated medical diagnoses, and examples from the authors’ collaborative research.
Tasks	Self-Driving Cars
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03779v1
PDF	http://arxiv.org/pdf/1712.03779v1.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-and-statistics
Repo
Framework

Abductive Matching in Question Answering


Title	Abductive Matching in Question Answering
Authors	Kedar Dhamdhere, Kevin S. McCurley, Mukund Sundararajan, Ankur Taly
Abstract	We study question-answering over semi-structured data. We introduce a new way to apply the technique of semantic parsing by applying machine learning only to provide annotations that the system infers to be missing; all the other parsing logic is in the form of manually authored rules. In effect, the machine learning is used to provide non-syntactic matches, a step that is ill-suited to manual rules. The advantage of this approach is in its debuggability and in its transparency to the end-user. We demonstrate the effectiveness of the approach by achieving state-of-the-art performance of 40.42% accuracy on a standard benchmark dataset over tables from Wikipedia.
Tasks	Question Answering, Semantic Parsing
Published	2017-09-10
URL	http://arxiv.org/abs/1709.03036v1
PDF	http://arxiv.org/pdf/1709.03036v1.pdf
PWC	https://paperswithcode.com/paper/abductive-matching-in-question-answering
Repo
Framework

Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces


Title	Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces
Authors	Daniel Levy, Stefano Ermon
Abstract	Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based methods greatly improve sample-efficiency but at the cost of poor generalization, requiring a carefully handcrafted model of the system dynamics for each task. Recently, hybrid methods have been successful in trading off applicability for improved sample-complexity. However, these have been limited to continuous action spaces. In this work, we present a new hybrid method based on an approximation of the dynamics as an expectation over the next state under the current policy. This relaxation allows us to derive a novel hybrid policy gradient estimator, combining score function and pathwise derivative estimators, that is applicable to discrete action spaces. We show significant gains in sample complexity, ranging between $1.7$ and $25\times$, when learning parameterized policies on Cart Pole, Acrobot, Mountain Car and Hand Mass. Our method is applicable to both discrete and continuous action spaces, when competing pathwise methods are limited to the latter.
Tasks	Imitation Learning
Published	2017-11-21
URL	http://arxiv.org/abs/1711.08068v1
PDF	http://arxiv.org/pdf/1711.08068v1.pdf
PWC	https://paperswithcode.com/paper/deterministic-policy-optimization-by
Repo
Framework

Multi-Glimpse LSTM with Color-Depth Feature Fusion for Human Detection


Title	Multi-Glimpse LSTM with Color-Depth Feature Fusion for Human Detection
Authors	Hengduo Li, Jun Liu, Guyue Zhang, Yuan Gao, Yirui Wu
Abstract	With the development of depth cameras such as Kinect and Intel Realsense, RGB-D based human detection receives continuous research attention due to its usage in a variety of applications. In this paper, we propose a new Multi-Glimpse LSTM (MG-LSTM) network, in which multi-scale contextual information is sequentially integrated to promote the human detection performance. Furthermore, we propose a feature fusion strategy based on our MG-LSTM network to better incorporate the RGB and depth information. To the best of our knowledge, this is the first attempt to utilize LSTM structure for RGB-D based human detection. Our method achieves superior performance on two publicly available datasets.
Tasks	Human Detection
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01062v1
PDF	http://arxiv.org/pdf/1711.01062v1.pdf
PWC	https://paperswithcode.com/paper/multi-glimpse-lstm-with-color-depth-feature
Repo
Framework