July 27, 2019

3171 words 15 mins read

Paper Group ANR 496

Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer. Segmentation of nearly isotropic overlapped tracks in photomicrographs using successive erosions as watershed markers. Object Tracking based on Quantum Particle Swarm Optimization. IQ of Neural Networks. Gender-From-Iris or Gender-From-Mascara?. Happin …

Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer


Title	Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer
Authors	Chongyi Li, Jichang Guo, Chunle Guo
Abstract	Underwater vision suffers from severe effects due to selective attenuation and scattering when light propagates through water. Such degradation not only affects the quality of underwater images but limits the ability of vision tasks. Different from existing methods which either ignore the wavelength dependency of the attenuation or assume a specific spectral profile, we tackle color distortion problem of underwater image from a new view. In this letter, we propose a weakly supervised color transfer method to correct color distortion, which relaxes the need of paired underwater images for training and allows for the underwater images unknown where were taken. Inspired by Cycle-Consistent Adversarial Networks, we design a multi-term loss function including adversarial loss, cycle consistency loss, and SSIM (Structural Similarity Index Measure) loss, which allows the content and structure of the corrected result the same as the input, but the color as if the image was taken without the water. Experiments on underwater images captured under diverse scenes show that our method produces visually pleasing results, even outperforms the art-of-the-state methods. Besides, our method can improve the performance of vision tasks.
Tasks
Published	2017-10-19
URL	http://arxiv.org/abs/1710.07084v3
PDF	http://arxiv.org/pdf/1710.07084v3.pdf
PWC	https://paperswithcode.com/paper/emerging-from-water-underwater-image-color
Repo
Framework

Segmentation of nearly isotropic overlapped tracks in photomicrographs using successive erosions as watershed markers


Title	Segmentation of nearly isotropic overlapped tracks in photomicrographs using successive erosions as watershed markers
Authors	Alexandre Fioravante de Siqueira, Wagner Massayuki Nakasuga, Sandro Guedes, Lothar Ratschbacher
Abstract	The major challenges of automatic track counting are distinguishing tracks and material defects, identifying small tracks and defects of similar size, and detecting overlapping tracks. Here we address the latter issue using WUSEM, an algorithm which combines the watershed transform, morphological erosions and labeling to separate regions in photomicrographs. WUSEM shows reliable results when used in photomicrographs presenting almost isotropic objects. We tested this method in two datasets of diallyl phthalate (DAP) photomicrographs and compared the results when counting manually and using the classic watershed. The mean automatic/manual efficiency ratio when using WUSEM in the test datasets is 0.97 +/- 0.11.
Tasks
Published	2017-06-10
URL	http://arxiv.org/abs/1706.03282v2
PDF	http://arxiv.org/pdf/1706.03282v2.pdf
PWC	https://paperswithcode.com/paper/segmentation-of-nearly-isotropic-overlapped
Repo
Framework

Object Tracking based on Quantum Particle Swarm Optimization


Title	Object Tracking based on Quantum Particle Swarm Optimization
Authors	Rajesh Misra, Kumar S. Ray
Abstract	In Computer Vision domain, moving Object Tracking considered as one of the toughest problem.As there so many factors associated like illumination of light, noise, occlusion, sudden start and stop of moving object, shading which makes tracking even harder problem not only for dynamic background but also for static background.In this paper we present a new object tracking algorithm based on Dominant points on tracked object using Quantum particle swarm optimization (QPSO) which is a new different version of PSO based on Quantum theory. The novelty in our approach is that it can be successfully applicable in variable background as well as static background and application of quantum PSO makes the algorithm runs lot faster where other basic PSO algorithm failed to do so due to heavy computation.In our approach firstly dominants points of tracked objects detected, then a group of particles form a swarm are initialized randomly over the image search space and then start searching the curvature connected between two consecutive dominant points until they satisfy fitness criteria. Obviously it is a Multi-Swarm approach as there are multiple dominant points, as they moves, the curvature moves and the curvature movement is tracked by the swarm throughout the video and eventually when the swarm reaches optimal solution , a bounding box drawn based on particles final position.Experimental results demonstrate this proposed QPSO based method work efficiently and effectively in visual object tracking in both dynamic and static environments and run time shows that it runs closely 90% faster than basic PSO.in our approach we also apply parallelism using MatLab Parfor command to show how very less number of iteration and swarm size will enable us to successfully track object.
Tasks	Image Retrieval, Object Tracking, Visual Object Tracking
Published	2017-05-24
URL	http://arxiv.org/abs/1707.05228v1
PDF	http://arxiv.org/pdf/1707.05228v1.pdf
PWC	https://paperswithcode.com/paper/object-tracking-based-on-quantum-particle
Repo
Framework

IQ of Neural Networks


Title	IQ of Neural Networks
Authors	Dokhyam Hoshen, Michael Werman
Abstract	IQ tests are an accepted method for assessing human intelligence. The tests consist of several parts that must be solved under a time constraint. Of all the tested abilities, pattern recognition has been found to have the highest correlation with general intelligence. This is primarily because pattern recognition is the ability to find order in a noisy environment, a necessary skill for intelligent agents. In this paper, we propose a convolutional neural network (CNN) model for solving geometric pattern recognition problems. The CNN receives as input multiple ordered input images and outputs the next image according to the pattern. Our CNN is able to solve problems involving rotation, reflection, color, size and shape patterns and score within the top 5% of human performance.
Tasks
Published	2017-09-29
URL	http://arxiv.org/abs/1710.01692v1
PDF	http://arxiv.org/pdf/1710.01692v1.pdf
PWC	https://paperswithcode.com/paper/iq-of-neural-networks
Repo
Framework

Gender-From-Iris or Gender-From-Mascara?


Title	Gender-From-Iris or Gender-From-Mascara?
Authors	Andrey Kuehlkamp, Benedict Becker, Kevin Bowyer
Abstract	Predicting a person’s gender based on the iris texture has been explored by several researchers. This paper considers several dimensions of experimental work on this problem, including person-disjoint train and test, and the effect of cosmetics on eyelash occlusion and imperfect segmentation. We also consider the use of multi-layer perceptron and convolutional neural networks as classifiers, comparing the use of data-driven and hand-crafted features. Our results suggest that the gender-from-iris problem is more difficult than has so far been appreciated. Estimating accuracy using a mean of N person-disjoint train and test partitions, and considering the effect of makeup - a combination of experimental conditions not present in any previous work - we find a much weaker ability to predict gender-from-iris texture than has been suggested in previous work.
Tasks
Published	2017-02-04
URL	http://arxiv.org/abs/1702.01304v1
PDF	http://arxiv.org/pdf/1702.01304v1.pdf
PWC	https://paperswithcode.com/paper/gender-from-iris-or-gender-from-mascara
Repo
Framework

Happiness Pursuit: Personality Learning in a Society of Agents


Title	Happiness Pursuit: Personality Learning in a Society of Agents
Authors	Rafał Muszyński, Jun Wang
Abstract	Modeling personality is a challenging problem with applications spanning computer games, virtual assistants, online shopping and education. Many techniques have been tried, ranging from neural networks to computational cognitive architectures. However, most approaches rely on examples with hand-crafted features and scenarios. Here, we approach learning a personality by training agents using a Deep Q-Network (DQN) model on rewards based on psychoanalysis, against hand-coded AI in the game of Pong. As a result, we obtain 4 agents, each with its own personality. Then, we define happiness of an agent, which can be seen as a measure of alignment with agent’s objective function, and study it when agents play both against hand-coded AI, and against each other. We find that the agents that achieve higher happiness during testing against hand-coded AI, have lower happiness when competing against each other. This suggests that higher happiness in testing is a sign of overfitting in learning to interact with hand-coded AI, and leads to worse performance against agents with different personalities.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.11068v2
PDF	http://arxiv.org/pdf/1711.11068v2.pdf
PWC	https://paperswithcode.com/paper/happiness-pursuit-personality-learning-in-a
Repo
Framework

Automatic Representation for Lifetime Value Recommender Systems


Title	Automatic Representation for Lifetime Value Recommender Systems
Authors	Assaf Hallak, Yishay Mansour, Elad Yom-Tov
Abstract	Many modern commercial sites employ recommender systems to propose relevant content to users. While most systems are focused on maximizing the immediate gain (clicks, purchases or ratings), a better notion of success would be the lifetime value (LTV) of the user-system interaction. The LTV approach considers the future implications of the item recommendation, and seeks to maximize the cumulative gain over time. The Reinforcement Learning (RL) framework is the standard formulation for optimizing cumulative successes over time. However, RL is rarely used in practice due to its associated representation, optimization and validation techniques which can be complex. In this paper we propose a new architecture for combining RL with recommendation systems which obviates the need for hand-tuned features, thus automating the state-space representation construction process. We analyze the practical difficulties in this formulation and test our solutions on batch off-line real-world recommendation data.
Tasks	Recommendation Systems
Published	2017-02-23
URL	http://arxiv.org/abs/1702.07125v1
PDF	http://arxiv.org/pdf/1702.07125v1.pdf
PWC	https://paperswithcode.com/paper/automatic-representation-for-lifetime-value
Repo
Framework

Eigen-Distortions of Hierarchical Representations


Title	Eigen-Distortions of Hierarchical Representations
Authors	Alexander Berardino, Johannes Ballé, Valero Laparra, Eero P. Simoncelli
Abstract	We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans. Specifically, we utilize Fisher information to establish a model-derived prediction of sensitivity to local perturbations of an image. For a given image, we compute the eigenvectors of the Fisher information matrix with largest and smallest eigenvalues, corresponding to the model-predicted most- and least-noticeable image distortions, respectively. For human subjects, we then measure the amount of each distortion that can be reliably detected when added to the image. We use this method to test the ability of a variety of representations to mimic human perceptual sensitivity. We find that the early layers of VGG16, a deep neural network optimized for object recognition, provide a better match to human perception than later layers, and a better match than a 4-stage convolutional neural network (CNN) trained on a database of human ratings of distorted image quality. On the other hand, we find that simple models of early visual processing, incorporating one or more stages of local gain control, trained on the same database of distortion ratings, provide substantially better predictions of human sensitivity than either the CNN, or any combination of layers of VGG16.
Tasks	Object Recognition
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02266v3
PDF	http://arxiv.org/pdf/1710.02266v3.pdf
PWC	https://paperswithcode.com/paper/eigen-distortions-of-hierarchical
Repo
Framework

A Context Aware and Video-Based Risk Descriptor for Cyclists


Title	A Context Aware and Video-Based Risk Descriptor for Cyclists
Authors	Miguel Costa, Beatriz Quintino Ferreira, Manuel Marques
Abstract	Aiming to reduce pollutant emissions, bicycles are regaining popularity specially in urban areas. However, the number of cyclists’ fatalities is not showing the same decreasing trend as the other traffic groups. Hence, monitoring cyclists’ data appears as a keystone to foster urban cyclists’ safety by helping urban planners to design safer cyclist routes. In this work, we propose a fully image-based framework to assess the rout risk from the cyclist perspective. From smartphone sequences of images, this generic framework is able to automatically identify events considering different risk criteria based on the cyclist’s motion and object detection. Moreover, since it is entirely based on images, our method provides context on the situation and is independent from the expertise level of the cyclist. Additionally, we build on an existing platform and introduce several improvements on its mobile app to acquire smartphone sensor data, including video. From the inertial sensor data, we automatically detect the route segments performed by bicycle, applying behavior analysis techniques. We test our methods on real data, attaining very promising results in terms of risk classification, according to two different criteria, and behavior analysis accuracy.
Tasks	Object Detection
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07490v1
PDF	http://arxiv.org/pdf/1704.07490v1.pdf
PWC	https://paperswithcode.com/paper/a-context-aware-and-video-based-risk
Repo
Framework

Model-free prediction of noisy chaotic time series by deep learning


Title	Model-free prediction of noisy chaotic time series by deep learning
Authors	Kyongmin Yeo
Abstract	We present a deep neural network for a model-free prediction of a chaotic dynamical system from noisy observations. The proposed deep learning model aims to predict the conditional probability distribution of a state variable. The Long Short-Term Memory network (LSTM) is employed to model the nonlinear dynamics and a softmax layer is used to approximate a probability distribution. The LSTM model is trained by minimizing a regularized cross-entropy function. The LSTM model is validated against delay-time chaotic dynamical systems, Mackey-Glass and Ikeda equations. It is shown that the present LSTM makes a good prediction of the nonlinear dynamics by effectively filtering out the noise. It is found that the prediction uncertainty of a multiple-step forecast of the LSTM model is not a monotonic function of time; the predicted standard deviation may increase or decrease dynamically in time.
Tasks	Time Series
Published	2017-09-29
URL	http://arxiv.org/abs/1710.01693v1
PDF	http://arxiv.org/pdf/1710.01693v1.pdf
PWC	https://paperswithcode.com/paper/model-free-prediction-of-noisy-chaotic-time
Repo
Framework

Automated Tumor Segmentation and Brain Mapping for the Tumor Area


Title	Automated Tumor Segmentation and Brain Mapping for the Tumor Area
Authors	Pranay Manocha, Snehal Bhasme, Tanvi Gupta, BK Panigrahi, Tapan K. Gandhi
Abstract	Magnetic Resonance Imaging (MRI) is an important diagnostic tool for precise detection of various pathologies. Magnetic Resonance (MR) is more preferred than Computed Tomography (CT) due to the high resolution in MR images which help in better detection of neurological conditions. Graphical user interface (GUI) aided disease detection has become increasingly useful due to the increasing workload of doctors. In this proposed work, a novel two steps GUI technique for brain tumor segmentation as well as Brodmann area detec-tion of the segmented tumor is proposed. A data set of T2 weighted images of 15 patients is used for validating the proposed method. The patient data incor-porates variations in ethnicities, gender (male and female) and age (25-50), thus enhancing the authenticity of the proposed method. The tumors were segmented using Fuzzy C Means Clustering and Brodmann area detection was done using a known template, mapping each area to the segmented tumor image. The proposed method was found to be fairly accurate and robust in detecting tumor.
Tasks	Brain Tumor Segmentation, Computed Tomography (CT)
Published	2017-10-28
URL	http://arxiv.org/abs/1710.11121v1
PDF	http://arxiv.org/pdf/1710.11121v1.pdf
PWC	https://paperswithcode.com/paper/automated-tumor-segmentation-and-brain
Repo
Framework

Learning Character-level Compositionality with Visual Features


Title	Learning Character-level Compositionality with Visual Features
Authors	Frederick Liu, Han Lu, Chieh Lo, Graham Neubig
Abstract	Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the character-level: the meaning of a character is derived by the sum of its parts. In this paper, we model this effect by creating embeddings for characters based on their visual characteristics, creating an image for the character and running it through a convolutional neural network to produce a visual character embedding. Experiments on a text classification task demonstrate that such model allows for better processing of instances with rare characters in languages such as Chinese, Japanese, and Korean. Additionally, qualitative analyses demonstrate that our proposed model learns to focus on the parts of characters that carry semantic content, resulting in embeddings that are coherent in visual space.
Tasks	Text Classification
Published	2017-04-17
URL	http://arxiv.org/abs/1704.04859v2
PDF	http://arxiv.org/pdf/1704.04859v2.pdf
PWC	https://paperswithcode.com/paper/learning-character-level-compositionality
Repo
Framework

Predicting membrane protein contacts from non-membrane proteins by deep transfer learning


Title	Predicting membrane protein contacts from non-membrane proteins by deep transfer learning
Authors	Zhen Li, Sheng Wang, Yizhou Yu, Jinbo Xu
Abstract	Computational prediction of membrane protein (MP) structures is very challenging partially due to lack of sufficient solved structures for homology modeling. Recently direct evolutionary coupling analysis (DCA) sheds some light on protein contact prediction and accordingly, contact-assisted folding, but DCA is effective only on some very large-sized families since it uses information only in a single protein family. This paper presents a deep transfer learning method that can significantly improve MP contact prediction by learning contact patterns and complex sequence-contact relationship from thousands of non-membrane proteins (non-MPs). Tested on 510 non-redundant MPs, our deep model (learned from only non-MPs) has top L/10 long-range contact prediction accuracy 0.69, better than our deep model trained by only MPs (0.63) and much better than a representative DCA method CCMpred (0.47) and the CASP11 winner MetaPSICOV (0.55). The accuracy of our deep model can be further improved to 0.72 when trained by a mix of non-MPs and MPs. When only contacts in transmembrane regions are evaluated, our method has top L/10 long-range accuracy 0.62, 0.57, and 0.53 when trained by a mix of non-MPs and MPs, by non-MPs only, and by MPs only, respectively, still much better than MetaPSICOV (0.45) and CCMpred (0.40). All these results suggest that sequence-structure relationship learned by our deep model from non-MPs generalizes well to MP contact prediction. Improved contact prediction also leads to better contact-assisted folding. Using only top predicted contacts as restraints, our deep learning method can fold 160 and 200 of 510 MPs with TMscore>0.6 when trained by non-MPs only and by a mix of non-MPs and MPs, respectively, while CCMpred and MetaPSICOV can do so for only 56 and 77 MPs, respectively. Our contact-assisted folding also greatly outperforms homology modeling.
Tasks	Transfer Learning
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07207v1
PDF	http://arxiv.org/pdf/1704.07207v1.pdf
PWC	https://paperswithcode.com/paper/predicting-membrane-protein-contacts-from-non
Repo
Framework

Identifying Similarities in Epileptic Patients for Drug Resistance Prediction


Title	Identifying Similarities in Epileptic Patients for Drug Resistance Prediction
Authors	David Von Dollen
Abstract	Currently, approximately 30% of epileptic patients treated with antiepileptic drugs (AEDs) remain resistant to treatment (known as refractory patients). This project seeks to understand the underlying similarities in refractory patients vs. other epileptic patients, identify features contributing to drug resistance across underlying phenotypes for refractory patients, and develop predictive models for drug resistance in epileptic patients. In this study, epileptic patient data was examined to attempt to observe discernable similarities or differences in refractory patients (case) and other non-refractory patients (control) to map underlying mechanisms in causality. For the first part of the study, unsupervised algorithms such as Kmeans, Spectral Clustering, and Gaussian Mixture Models were used to examine patient features projected into a lower dimensional space. Results from this study showed a high degree of non-linearity in the underlying feature space. For the second part of this study, classification algorithms such as Logistic Regression, Gradient Boosted Decision Trees, and SVMs, were tested on the reduced-dimensionality features, with accuracy results of 0.83(+/-0.3) testing using 7 fold cross validation. Observations of test results indicate using a radial basis function kernel PCA to reduce features ingested by a Gradient Boosted Decision Tree Ensemble lead to gains in improved accuracy in mapping a binary decision to highly non-linear features collected from epileptic patients.
Tasks
Published	2017-04-26
URL	http://arxiv.org/abs/1704.08361v1
PDF	http://arxiv.org/pdf/1704.08361v1.pdf
PWC	https://paperswithcode.com/paper/identifying-similarities-in-epileptic
Repo
Framework

Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder


Title	Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder
Authors	Huadong Chen, Shujian Huang, David Chiang, Jiajun Chen
Abstract	Most neural machine translation (NMT) models are based on the sequential encoder-decoder framework, which makes no use of syntactic information. In this paper, we improve this model by explicitly incorporating source-side syntactic trees. More specifically, we propose (1) a bidirectional tree encoder which learns both sequential and tree structured representations; (2) a tree-coverage model that lets the attention depend on the source-side syntax. Experiments on Chinese-English translation demonstrate that our proposed models outperform the sequential attentional model as well as a stronger baseline with a bottom-up tree encoder and word coverage.
Tasks	Machine Translation
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05436v1
PDF	http://arxiv.org/pdf/1707.05436v1.pdf
PWC	https://paperswithcode.com/paper/improved-neural-machine-translation-with-a
Repo
Framework