October 17, 2019

3084 words 15 mins read

Paper Group ANR 842

Robust Propensity Score Computation Method based on Machine Learning with Label-corrupted Data. PHI Scrubber: A Deep Learning Approach. Wireless Software Synchronization of Multiple Distributed Cameras. Sentiment Analysis of Comments on Rohingya Movement with Support Vector Machine. Pragmatically Informative Image Captioning with Character-Level In …

Robust Propensity Score Computation Method based on Machine Learning with Label-corrupted Data


Title	Robust Propensity Score Computation Method based on Machine Learning with Label-corrupted Data
Authors	Chen Wang, Suzhen Wang, Fuyan Shi, Zaixiang Wang
Abstract	In biostatistics, propensity score is a common approach to analyze the imbalance of covariate and process confounding covariates to eliminate differences between groups. While there are an abundant amount of methods to compute propensity score, a common issue of them is the corrupted labels in the dataset. For example, the data collected from the patients could contain samples that are treated mistakenly, and the computing methods could incorporate them as a misleading information. In this paper, we propose a Machine Learning-based method to handle the problem. Specifically, we utilize the fact that the majority of sample should be labeled with the correct instance and design an approach to first cluster the data with spectral clustering and then sample a new dataset with a distribution processed from the clustering results. The propensity score is computed by Xgboost, and a mathematical justification of our method is provided in this paper. The experimental results illustrate that xgboost propensity scores computing with the data processed by our method could outperform the same method with original data, and the advantages of our method increases as we add some artificial corruptions to the dataset. Meanwhile, the implementation of xgboost to compute propensity score for multiple treatments is also a pioneering work in the area.
Tasks
Published	2018-01-09
URL	http://arxiv.org/abs/1801.03132v1
PDF	http://arxiv.org/pdf/1801.03132v1.pdf
PWC	https://paperswithcode.com/paper/robust-propensity-score-computation-method
Repo
Framework

PHI Scrubber: A Deep Learning Approach


Title	PHI Scrubber: A Deep Learning Approach
Authors	Abhai Kollara Dilip, Kamal Raj K, Malaikannan Sankarasubbu
Abstract	Confidentiality of patient information is an essential part of Electronic Health Record System. Patient information, if exposed, can cause a serious damage to the privacy of individuals receiving healthcare. Hence it is important to remove such details from physician notes. A system is proposed which consists of a deep learning model where a de-convolutional neural network and bi-directional LSTM-CNN is used along with regular expressions to recognize and eliminate the individually identifiable information. This information is then removed from a medical practitioner’s data which further allows the fair usage of such information among researchers and in clinical trials.
Tasks
Published	2018-08-03
URL	http://arxiv.org/abs/1808.01128v1
PDF	http://arxiv.org/pdf/1808.01128v1.pdf
PWC	https://paperswithcode.com/paper/phi-scrubber-a-deep-learning-approach
Repo
Framework

Wireless Software Synchronization of Multiple Distributed Cameras


Title	Wireless Software Synchronization of Multiple Distributed Cameras
Authors	Sameer Ansari, Neal Wadhwa, Rahul Garg, Jiawen Chen
Abstract	We present a method for precisely time-synchronizing the capture of image sequences from a collection of smartphone cameras connected over WiFi. Our method is entirely software-based, has only modest hardware requirements, and achieves an accuracy of less than 250 microseconds on unmodified commodity hardware. It does not use image content and synchronizes cameras prior to capture. The algorithm operates in two stages. In the first stage, we designate one device as the leader and synchronize each client device’s clock to it by estimating network delay. Once clocks are synchronized, the second stage initiates continuous image streaming, estimates the relative phase of image timestamps between each client and the leader, and shifts the streams into alignment. We quantitatively validate our results on a multi-camera rig imaging a high-precision LED array and qualitatively demonstrate significant improvements to multi-view stereo depth estimation and stitching of dynamic scenes. We release as open source ‘libsoftwaresync’, an Android implementation of our system, to inspire new types of collective capture applications.
Tasks	Depth Estimation, Stereo Depth Estimation
Published	2018-12-21
URL	https://arxiv.org/abs/1812.09366v2
PDF	https://arxiv.org/pdf/1812.09366v2.pdf
PWC	https://paperswithcode.com/paper/wireless-software-synchronization-of-multiple
Repo
Framework

Sentiment Analysis of Comments on Rohingya Movement with Support Vector Machine


Title	Sentiment Analysis of Comments on Rohingya Movement with Support Vector Machine
Authors	Hemayet Ahmed Chowdhury, Tanvir Alam Nibir, Md. Saiful Islam
Abstract	The Rohingya Movement and Crisis caused a huge uproar in the political and economic state of Bangladesh. Refugee movement is a recurring event and a large amount of data in the form of opinions remains on social media such as Facebook, with very little analysis done on them.To analyse the comments based on all Rohingya related posts, we had to create and modify a classifier based on the Support Vector Machine algorithm. The code is implemented in python and uses scikit-learn library. A dataset on Rohingya analysis is not currently available so we had to use our own data set of 2500 positive and 2500 negative comments. We specifically used a support vector machine with linear kernel. A previous experiment was performed by us on the same dataset using the naive bayes algorithm, but that did not yield impressive results.
Tasks	Sentiment Analysis
Published	2018-03-22
URL	http://arxiv.org/abs/1803.08790v1
PDF	http://arxiv.org/pdf/1803.08790v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-of-comments-on-rohingya
Repo
Framework

Pragmatically Informative Image Captioning with Character-Level Inference


Title	Pragmatically Informative Image Captioning with Character-Level Inference
Authors	Reuben Cohn-Gordon, Noah Goodman, Christopher Potts
Abstract	We combine a neural image captioner with a Rational Speech Acts (RSA) model to make a system that is pragmatically informative: its objective is to produce captions that are not merely true but also distinguish their inputs from similar images. Previous attempts to combine RSA with neural image captioning require an inference which normalizes over the entire set of possible utterances. This poses a serious problem of efficiency, previously solved by sampling a small subset of possible utterances. We instead solve this problem by implementing a version of RSA which operates at the level of characters (“a”,“b”,“c”…) during the unrolling of the caption. We find that the utterance-level effect of referential captions can be obtained with only character-level decisions. Finally, we introduce an automatic method for testing the performance of pragmatic speaker models, and show that our model outperforms a non-pragmatic baseline as well as a word-level RSA captioner.
Tasks	Image Captioning
Published	2018-04-15
URL	http://arxiv.org/abs/1804.05417v2
PDF	http://arxiv.org/pdf/1804.05417v2.pdf
PWC	https://paperswithcode.com/paper/pragmatically-informative-image-captioning
Repo
Framework

Text Classification based on Word Subspace with Term-Frequency


Title	Text Classification based on Word Subspace with Term-Frequency
Authors	Erica K. Shimomoto, Lincon S. Souza, Bernardo B. Gatto, Kazuhiro Fukui
Abstract	Text classification has become indispensable due to the rapid increase of text in digital form. Over the past three decades, efforts have been made to approach this task using various learning algorithms and statistical models based on bag-of-words (BOW) features. Despite its simple implementation, BOW features lack semantic meaning representation. To solve this problem, neural networks started to be employed to learn word vectors, such as the word2vec. Word2vec embeds word semantic structure into vectors, where the angle between vectors indicates the meaningful similarity between words. To measure the similarity between texts, we propose the novel concept of word subspace, which can represent the intrinsic variability of features in a set of word vectors. Through this concept, it is possible to model text from word vectors while holding semantic information. To incorporate the word frequency directly in the subspace model, we further extend the word subspace to the term-frequency (TF) weighted word subspace. Based on these new concepts, text classification can be performed under the mutual subspace method (MSM) framework. The validity of our modeling is shown through experiments on the Reuters text database, comparing the results to various state-of-art algorithms.
Tasks	Text Classification
Published	2018-06-08
URL	http://arxiv.org/abs/1806.03125v1
PDF	http://arxiv.org/pdf/1806.03125v1.pdf
PWC	https://paperswithcode.com/paper/text-classification-based-on-word-subspace
Repo
Framework

Attentive Crowd Flow Machines


Title	Attentive Crowd Flow Machines
Authors	Lingbo Liu, Ruimao Zhang, Jiefeng Peng, Guanbin Li, Bowen Du, Liang Lin
Abstract	Traffic flow prediction is crucial for urban traffic management and public safety. Its key challenges lie in how to adaptively integrate the various factors that affect the flow changes. In this paper, we propose a unified neural network module to address this problem, called Attentive Crowd Flow Machine~(ACFM), which is able to infer the evolution of the crowd flow by learning dynamic representations of temporally-varying data with an attention mechanism. Specifically, the ACFM is composed of two progressive ConvLSTM units connected with a convolutional layer for spatial weight prediction. The first LSTM takes the sequential flow density representation as input and generates a hidden state at each time-step for attention map inference, while the second LSTM aims at learning the effective spatial-temporal feature expression from attentionally weighted crowd flow features. Based on the ACFM, we further build a deep architecture with the application to citywide crowd flow prediction, which naturally incorporates the sequential and periodic data as well as other external influences. Extensive experiments on two standard benchmarks (i.e., crowd flow in Beijing and New York City) show that the proposed method achieves significant improvements over the state-of-the-art methods.
Tasks
Published	2018-09-01
URL	http://arxiv.org/abs/1809.00101v1
PDF	http://arxiv.org/pdf/1809.00101v1.pdf
PWC	https://paperswithcode.com/paper/attentive-crowd-flow-machines
Repo
Framework

Deep Learning Approach for Very Similar Objects Recognition Application on Chihuahua and Muffin Problem


Title	Deep Learning Approach for Very Similar Objects Recognition Application on Chihuahua and Muffin Problem
Authors	Enkhtogtokh Togootogtokh, Amarzaya Amartuvshin
Abstract	We address the problem to tackle the very similar objects like Chihuahua or muffin problem to recognize at least in human vision level. Our regular deep structured machine learning still does not solve it. We saw many times for about year in our community the problem. Today we proposed the state-of-the-art solution for it. Our approach is quite tricky to get the very high accuracy. We propose the deep transfer learning method which could be tackled all this type of problems not limited to just Chihuahua or muffin problem. It is the best method to train with small data set not like require huge amount data.
Tasks	Transfer Learning
Published	2018-01-29
URL	http://arxiv.org/abs/1801.09573v1
PDF	http://arxiv.org/pdf/1801.09573v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-approach-for-very-similar
Repo
Framework

Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks


Title	Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks
Authors	Sorour Mohajerani, Thomas A. Krammer, Parvaneh Saeedi
Abstract	This paper presents a deep-learning based framework for addressing the problem of accurate cloud detection in remote sensing images. This framework benefits from a Fully Convolutional Neural Network (FCN), which is capable of pixel-level labeling of cloud regions in a Landsat 8 image. Also, a gradient-based identification approach is proposed to identify and exclude regions of snow/ice in the ground truths of the training set. We show that using the hybrid of the two methods (threshold-based and deep-learning) improves the performance of the cloud identification process without the need to manually correct automatically generated ground truths. In average the Jaccard index and recall measure are improved by 4.36% and 3.62%, respectively.
Tasks	Cloud Detection
Published	2018-10-13
URL	http://arxiv.org/abs/1810.05782v1
PDF	http://arxiv.org/pdf/1810.05782v1.pdf
PWC	https://paperswithcode.com/paper/cloud-detection-algorithm-for-remote-sensing
Repo
Framework

Fire detection in a still image using colour information


Title	Fire detection in a still image using colour information
Authors	Oluwarotimi Giwa, Abdsamad Benkrid
Abstract	Colour analysis is a crucial step in image-based fire detection algorithms. Many of the proposed fire detection algorithms in a still image are prone to false alarms caused by objects with a colour similar to fire. To design a colour-based system with a better false alarm rate, a new colour-differentiating conversion matrix, efficient on images of high colour complexity, is proposed. The elements of this conversion matrix are obtained by performing K-medoids clustering and Particle Swarm Optimisation procedures on a fire sample image with a background of high fire-colour similarity. The proposed conversion matrix is then used to construct two new fire colour detection frameworks. The first detection method is a two-stage non-linear image transformation framework, while the second is a direct transformation of an image with the proposed conversion matrix. A performance comparison of the proposed methods with alternate methods in the literature was carried out. Experimental results indicate that the linear image transformation method outperforms other methods regarding false alarm rate while the non-linear two-stage image transformation method has the best performance on the F-score metric and provides a better trade-off between missed detection and false alarm rate.
Tasks
Published	2018-03-10
URL	http://arxiv.org/abs/1803.03828v1
PDF	http://arxiv.org/pdf/1803.03828v1.pdf
PWC	https://paperswithcode.com/paper/fire-detection-in-a-still-image-using-colour
Repo
Framework

Very Power Efficient Neural Time-of-Flight


Title	Very Power Efficient Neural Time-of-Flight
Authors	Yan Chen, Jimmy Ren, Xuanye Cheng, Keyuan Qian, Jinwei Gu
Abstract	Time-of-Flight (ToF) cameras require active illumination to obtain depth information thus the power of illumination directly affects the performance of ToF cameras. Traditional ToF imaging algorithms is very sensitive to illumination and the depth accuracy degenerates rapidly with the power of it. Therefore, the design of a power efficient ToF camera always creates a painful dilemma for the illumination and the performance trade-off. In this paper, we show that despite the weak signals in many areas under extreme short exposure setting, these signals as a whole can be well utilized through a learning process which directly translates the weak and noisy ToF camera raw to depth map. This creates an opportunity to tackle the aforementioned dilemma and make a very power efficient ToF camera possible. To enable the learning, we collect a comprehensive dataset under a variety of scenes and photographic conditions by a specialized ToF camera. Experiments show that our method is able to robustly process ToF camera raw with the exposure time of one order of magnitude shorter than that used in conventional ToF cameras. In addition to evaluating our approach both quantitatively and qualitatively, we also discuss its implication to designing the next generation power efficient ToF cameras. We will make our dataset and code publicly available.
Tasks
Published	2018-12-19
URL	http://arxiv.org/abs/1812.08125v1
PDF	http://arxiv.org/pdf/1812.08125v1.pdf
PWC	https://paperswithcode.com/paper/very-power-efficient-neural-time-of-flight
Repo
Framework

Variational Inference In Pachinko Allocation Machines


Title	Variational Inference In Pachinko Allocation Machines
Authors	Akash Srivastava, Charles Sutton
Abstract	The Pachinko Allocation Machine (PAM) is a deep topic model that allows representing rich correlation structures among topics by a directed acyclic graph over topics. Because of the flexibility of the model, however, approximate inference is very difficult. Perhaps for this reason, only a small number of potential PAM architectures have been explored in the literature. In this paper we present an efficient and flexible amortized variational inference method for PAM, using a deep inference network to parameterize the approximate posterior distribution in a manner similar to the variational autoencoder. Our inference method produces more coherent topics than state-of-art inference methods for PAM while being an order of magnitude faster, which allows exploration of a wider range of PAM architectures than have previously been studied.
Tasks
Published	2018-04-21
URL	http://arxiv.org/abs/1804.07944v1
PDF	http://arxiv.org/pdf/1804.07944v1.pdf
PWC	https://paperswithcode.com/paper/variational-inference-in-pachinko-allocation
Repo
Framework

Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech


Title	Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech
Authors	Aditya Deshpande, Jyoti Aneja, Liwei Wang, Alexander Schwing, D. A. Forsyth
Abstract	Image captioning is an ambiguous problem, with many suitable captions for an image. To address ambiguity, beam search is the de facto method for sampling multiple captions. However, beam search is computationally expensive and known to produce generic captions. To address this concern, some variational auto-encoder (VAE) and generative adversarial net (GAN) based methods have been proposed. Though diverse, GAN and VAE are less accurate. In this paper, we first predict a meaningful summary of the image, then generate the caption based on that summary. We use part-of-speech as summaries, since our summary should drive caption generation. We achieve the trifecta: (1) High accuracy for the diverse captions as evaluated by standard captioning metrics and user studies; (2) Faster computation of diverse captions compared to beam search and diverse beam search; and (3) High diversity as evaluated by counting novel sentences, distinct n-grams and mutual overlap (i.e., mBleu-4) scores.
Tasks	Image Captioning
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12589v3
PDF	http://arxiv.org/pdf/1805.12589v3.pdf
PWC	https://paperswithcode.com/paper/fast-diverse-and-accurate-image-captioning
Repo
Framework

Weak-supervision for Deep Representation Learning under Class Imbalance


Title	Weak-supervision for Deep Representation Learning under Class Imbalance
Authors	Shin Ando
Abstract	Class imbalance is a pervasive issue among classification models including deep learning, whose capacity to extract task-specific features is affected in imbalanced settings. However, the challenges of handling imbalance among a large number of classes, commonly addressed by deep learning, have not received a significant amount of attention in previous studies. In this paper, we propose an extension of the deep over-sampling framework, to exploit automatically-generated abstract-labels, i.e., a type of side-information used in weak-label learning, to enhance deep representation learning against class imbalance. We attempt to exploit the labels to guide the deep representation of instances towards different subspaces, to induce a soft-separation of inherent subtasks of the classification problem. Our empirical study shows that the proposed framework achieves a substantial improvement on image classification benchmarks with imbalanced among large and small numbers of classes.
Tasks	Image Classification, Representation Learning
Published	2018-10-30
URL	http://arxiv.org/abs/1810.12513v1
PDF	http://arxiv.org/pdf/1810.12513v1.pdf
PWC	https://paperswithcode.com/paper/weak-supervision-for-deep-representation
Repo
Framework

Learning to Unlearn: Building Immunity to Dataset Bias in Medical Imaging Studies


Title	Learning to Unlearn: Building Immunity to Dataset Bias in Medical Imaging Studies
Authors	Ahmed Ashraf, Shehroz Khan, Nikhil Bhagwat, Mallar Chakravarty, Babak Taati
Abstract	Medical imaging machine learning algorithms are usually evaluated on a single dataset. Although training and testing are performed on different subsets of the dataset, models built on one study show limited capability to generalize to other studies. While database bias has been recognized as a serious problem in the computer vision community, it has remained largely unnoticed in medical imaging research. Transfer learning thus remains confined to the re-use of feature representations requiring re-training on the new dataset. As a result, machine learning models do not generalize even when trained on imaging datasets that were captured to study the same variable of interest. The ability to transfer knowledge gleaned from one study to another, without the need for re-training, if possible, would provide reassurance that the models are learning knowledge fundamental to the problem under study instead of latching onto the idiosyncracies of a dataset. In this paper, we situate the problem of dataset bias in the context of medical imaging studies. We show empirical evidence that such a problem exists in medical datasets. We then present a framework to unlearn study membership as a means to handle the problem of database bias. Our main idea is to take the data from the original feature space to an intermediate space where the data points are indistinguishable in terms of which study they come from, while maintaining the recognition capability with respect to the variable of interest. This will promote models which learn the more general properties of the etiology under study instead of aligning to dataset-specific peculiarities. Essentially, our proposed model learns to unlearn the dataset bias.
Tasks	Transfer Learning
Published	2018-12-03
URL	http://arxiv.org/abs/1812.01716v1
PDF	http://arxiv.org/pdf/1812.01716v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-unlearn-building-immunity-to
Repo
Framework