April 1, 2020

2874 words 14 mins read

Paper Group ANR 481

Paper Group ANR 481

C-DLinkNet: considering multi-level semantic features for human parsing. Intrinsic Motivation for Encouraging Synergistic Behavior. Learning to Represent Programs with Property Signatures. Segmentation of brain tumor on magnetic resonance imaging using a convolutional architecture. From Nesterov’s Estimate Sequence to Riemannian Acceleration. A Lab …

C-DLinkNet: considering multi-level semantic features for human parsing

Title C-DLinkNet: considering multi-level semantic features for human parsing
Authors Yu Lu, Muyan Feng, Ming Wu, Chuang Zhang
Abstract Human parsing is an essential branch of semantic segmentation, which is a fine-grained semantic segmentation task to identify the constituent parts of human. The challenge of human parsing is to extract effective semantic features to resolve deformation and multi-scale variations. In this work, we proposed an end-to-end model called C-DLinkNet based on LinkNet, which contains a new module named Smooth Module to combine the multi-level features in Decoder part. C-DLinkNet is capable of producing competitive parsing performance compared with the state-of-the-art methods with smaller input sizes and no additional information, i.e., achiving mIoU=53.05 on the validation set of LIP dataset.
Tasks Human Parsing, Semantic Segmentation
Published 2020-01-31
URL https://arxiv.org/abs/2001.11690v1
PDF https://arxiv.org/pdf/2001.11690v1.pdf
PWC https://paperswithcode.com/paper/c-dlinknet-considering-multi-level-semantic
Repo
Framework

Intrinsic Motivation for Encouraging Synergistic Behavior

Title Intrinsic Motivation for Encouraging Synergistic Behavior
Authors Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta, Abhinav Gupta
Abstract We study the role of intrinsic motivation as an exploration bias for reinforcement learning in sparse-reward synergistic tasks, which are tasks where multiple agents must work together to achieve a goal they could not individually. Our key idea is that a good guiding principle for intrinsic motivation in synergistic tasks is to take actions which affect the world in ways that would not be achieved if the agents were acting on their own. Thus, we propose to incentivize agents to take (joint) actions whose effects cannot be predicted via a composition of the predicted effect for each individual agent. We study two instantiations of this idea, one based on the true states encountered, and another based on a dynamics model trained concurrently with the policy. While the former is simpler, the latter has the benefit of being analytically differentiable with respect to the action taken. We validate our approach in robotic bimanual manipulation and multi-agent locomotion tasks with sparse rewards; we find that our approach yields more efficient learning than both 1) training with only the sparse reward and 2) using the typical surprise-based formulation of intrinsic motivation, which does not bias toward synergistic behavior. Videos are available on the project webpage: https://sites.google.com/view/iclr2020-synergistic.
Tasks
Published 2020-02-12
URL https://arxiv.org/abs/2002.05189v1
PDF https://arxiv.org/pdf/2002.05189v1.pdf
PWC https://paperswithcode.com/paper/intrinsic-motivation-for-encouraging-1
Repo
Framework

Learning to Represent Programs with Property Signatures

Title Learning to Represent Programs with Property Signatures
Authors Augustus Odena, Charles Sutton
Abstract We introduce the notion of property signatures, a representation for programs and program specifications meant for consumption by machine learning algorithms. Given a function with input type $\tau_{in}$ and output type $\tau_{out}$, a property is a function of type: $(\tau_{in}, \tau_{out}) \rightarrow \texttt{Bool}$ that (informally) describes some simple property of the function under consideration. For instance, if $\tau_{in}$ and $\tau_{out}$ are both lists of the same type, one property might ask is the input list the same length as the output list?'. If we have a list of such properties, we can evaluate them all for our function to get a list of outputs that we will call the property signature. Crucially, we can guess’ the property signature for a function given only a set of input/output pairs meant to specify that function. We discuss several potential applications of property signatures and show experimentally that they can be used to improve over a baseline synthesizer so that it emits twice as many programs in less than one-tenth of the time.
Tasks
Published 2020-02-13
URL https://arxiv.org/abs/2002.09030v1
PDF https://arxiv.org/pdf/2002.09030v1.pdf
PWC https://paperswithcode.com/paper/learning-to-represent-programs-with-property-1
Repo
Framework

Segmentation of brain tumor on magnetic resonance imaging using a convolutional architecture

Title Segmentation of brain tumor on magnetic resonance imaging using a convolutional architecture
Authors Miriam Zulema Jacobo, Jose Mejia
Abstract The brain is a complex organ controlling cognitive process and physical functions. Tumors in the brain are accelerated cell growths affecting the normal function and processes in the brain. MRI scans provides detailed images of the body being one of the most common tests to diagnose brain tumors. The process of segmentation of brain tumors from magnetic resonance imaging can provide a valuable guide for diagnosis, treatment planning and prediction of results. Here we consider the problem brain tumor segmentation using a Deep learning architecture for use in tumor segmentation. Although the proposed architecture is simple and computationally easy to train, it is capable of reaching $IoU$ levels of 0.95.
Tasks Brain Tumor Segmentation
Published 2020-03-17
URL https://arxiv.org/abs/2003.07934v1
PDF https://arxiv.org/pdf/2003.07934v1.pdf
PWC https://paperswithcode.com/paper/segmentation-of-brain-tumor-on-magnetic
Repo
Framework

From Nesterov’s Estimate Sequence to Riemannian Acceleration

Title From Nesterov’s Estimate Sequence to Riemannian Acceleration
Authors Kwangjun Ahn, Suvrit Sra
Abstract We propose the first global accelerated gradient method for Riemannian manifolds. Toward establishing our result we revisit Nesterov’s estimate sequence technique and develop an alternative analysis for it that may also be of independent interest. Then, we extend this analysis to the Riemannian setting, localizing the key difficulty due to non-Euclidean structure into a certain ``metric distortion.’’ We control this distortion by developing a novel geometric inequality, which permits us to propose and analyze a Riemannian counterpart to Nesterov’s accelerated gradient method. |
Tasks
Published 2020-01-24
URL https://arxiv.org/abs/2001.08876v1
PDF https://arxiv.org/pdf/2001.08876v1.pdf
PWC https://paperswithcode.com/paper/from-nesterovs-estimate-sequence-to
Repo
Framework

A Label Proportions Estimation Technique for Adversarial Domain Adaptation in Text Classification

Title A Label Proportions Estimation Technique for Adversarial Domain Adaptation in Text Classification
Authors Zhuohao Chen, Singla Karan, David C. Atkins, Zac E Imel, Shrikanth Narayanan
Abstract Many text classification tasks are domain-dependent, and various domain adaptation approaches have been proposed to predict unlabeled data in a new domain. Domain-adversarial neural networks (DANN) and their variants have been used widely recently and have achieved promising results for this problem. However, most of these approaches assume that the label proportions of the source and target domains are similar, which rarely holds in most real-world scenarios. Sometimes the label shift can be large and the DANN fails to learn domain-invariant features. In this study, we focus on unsupervised domain adaptation of text classification with label shift and introduce a domain adversarial network with label proportions estimation (DAN-LPE) framework. The DAN-LPE simultaneously trains a domain adversarial net and processes label proportions estimation by the confusion of the source domain and the predictions of the target domain. Experiments show the DAN-LPE achieves a good estimate of the target label distributions and reduces the label shift to improve the classification performance.
Tasks Domain Adaptation, Text Classification, Unsupervised Domain Adaptation
Published 2020-03-16
URL https://arxiv.org/abs/2003.07444v3
PDF https://arxiv.org/pdf/2003.07444v3.pdf
PWC https://paperswithcode.com/paper/a-label-proportions-estimation-technique-for
Repo
Framework

Brain Age Estimation Using LSTM on Children’s Brain MRI

Title Brain Age Estimation Using LSTM on Children’s Brain MRI
Authors Sheng He, Randy L. Gollub, Shawn N. Murphy, Juan David Perez, Sanjay Prabhu, Rudolph Pienaar, Richard L. Robertson, P. Ellen Grant, Yangming Ou
Abstract Brain age prediction based on children’s brain MRI is an important biomarker for brain health and brain development analysis. In this paper, we consider the 3D brain MRI volume as a sequence of 2D images and propose a new framework using the recurrent neural network for brain age estimation. The proposed method is named as 2D-ResNet18+Long short-term memory (LSTM), which consists of four parts: 2D ResNet18 for feature extraction on 2D images, a pooling layer for feature reduction over the sequences, an LSTM layer, and a final regression layer. We apply the proposed method on a public multisite NIH-PD dataset and evaluate generalization on a second multisite dataset, which shows that the proposed 2D-ResNet18+LSTM method provides better results than traditional 3D based neural network for brain age estimation.
Tasks Age Estimation
Published 2020-02-20
URL https://arxiv.org/abs/2002.09045v1
PDF https://arxiv.org/pdf/2002.09045v1.pdf
PWC https://paperswithcode.com/paper/brain-age-estimation-using-lstm-on-childrens
Repo
Framework

An Overview of Two Age Synthesis and Estimation Techniques

Title An Overview of Two Age Synthesis and Estimation Techniques
Authors Milad Taleby Ahvanooey, Qianmu Li
Abstract Age estimation is a technique for predicting human ages from digital facial images, which analyzes a person’s face image and estimates his/her age based on the year measure. Nowadays, intelligent age estimation and age synthesis have become particularly prevalent research topics in computer vision and face verification systems. Age synthesis is defined to render a facial image aesthetically with rejuvenating and natural aging effects on the person’s face. Age estimation is defined to label a facial image automatically with the age group (year range) or the exact age (year) of the person’s face. In this case study, we overview the existing models, popular techniques, system performances, and technical challenges related to the facial image-based age synthesis and estimation topics. The main goal of this review is to provide an easy understanding and promising future directions with systematic discussions.
Tasks Age Estimation, Face Verification
Published 2020-01-26
URL https://arxiv.org/abs/2002.03750v1
PDF https://arxiv.org/pdf/2002.03750v1.pdf
PWC https://paperswithcode.com/paper/an-overview-of-two-age-synthesis-and
Repo
Framework

Perfecting the Crime Machine

Title Perfecting the Crime Machine
Authors Yigit Alparslan, Ioanna Panagiotou, Willow Livengood, Robert Kane, Andrew Cohen
Abstract This study explores using different machine learning techniques and workflows to predict crime related statistics, specifically crime type in Philadelphia. We use crime location and time as main features, extract different features from the two features that our raw data has, and build models that would work with large number of class labels. We use different techniques to extract various features including combining unsupervised learning techniques and try to predict the crime type. Some of the models that we use are Support Vector Machines, Decision Trees, Random Forest, K-Nearest Neighbors. We report that the Random Forest as the best performing model to predict crime type with an error log loss of 2.3120.
Tasks
Published 2020-01-14
URL https://arxiv.org/abs/2001.09764v1
PDF https://arxiv.org/pdf/2001.09764v1.pdf
PWC https://paperswithcode.com/paper/perfecting-the-crime-machine
Repo
Framework

Understanding the Prediction Mechanism of Sentiments by XAI Visualization

Title Understanding the Prediction Mechanism of Sentiments by XAI Visualization
Authors Chaehan So
Abstract People often rely on online reviews to make purchase decisions. The present work aimed to gain an understanding of a machine learning model’s prediction mechanism by visualizing the effect of sentiments extracted from online hotel reviews with explainable AI (XAI) methodology. Study 1 used the extracted sentiments as features to predict the review ratings by five machine learning algorithms (knn, CART decision trees, support vector machines, random forests, gradient boosting machines) and identified random forests as best algorithm. Study 2 analyzed the random forests model by feature importance and revealed the sentiments joy, disgust, positive and negative as the most predictive features. Furthermore, the visualization of additive variable attributions and their prediction distribution showed correct prediction in direction and effect size for the 5-star rating but partially wrong direction and insufficient effect size for the 1-star rating. These prediction details were corroborated by a what-if analysis for the four top features. In conclusion, the prediction mechanism of a machine learning model can be uncovered by visualization of particular observations. Comparing instances of contrasting ground truth values can draw a differential picture of the prediction mechanism and inform decisions for model improvement.
Tasks Feature Importance
Published 2020-03-03
URL https://arxiv.org/abs/2003.01425v1
PDF https://arxiv.org/pdf/2003.01425v1.pdf
PWC https://paperswithcode.com/paper/understanding-the-prediction-mechanism-of
Repo
Framework

Local Policy Optimization for Trajectory-Centric Reinforcement Learning

Title Local Policy Optimization for Trajectory-Centric Reinforcement Learning
Authors Patrik Kolaric, Devesh K. Jha, Arvind U. Raghunathan, Frank L. Lewis, Mouhacine Benosman, Diego Romeres, Daniel Nikovski
Abstract The goal of this paper is to present a method for simultaneous trajectory and local stabilizing policy optimization to generate local policies for trajectory-centric model-based reinforcement learning (MBRL). This is motivated by the fact that global policy optimization for non-linear systems could be a very challenging problem both algorithmically and numerically. However, a lot of robotic manipulation tasks are trajectory-centric, and thus do not require a global model or policy. Due to inaccuracies in the learned model estimates, an open-loop trajectory optimization process mostly results in very poor performance when used on the real system. Motivated by these problems, we try to formulate the problem of trajectory optimization and local policy synthesis as a single optimization problem. It is then solved simultaneously as an instance of nonlinear programming. We provide some results for analysis as well as achieved performance of the proposed technique under some simplifying assumptions.
Tasks
Published 2020-01-22
URL https://arxiv.org/abs/2001.08092v1
PDF https://arxiv.org/pdf/2001.08092v1.pdf
PWC https://paperswithcode.com/paper/local-policy-optimization-for-trajectory
Repo
Framework

Privacy-Aware Time-Series Data Sharing with Deep Reinforcement Learning

Title Privacy-Aware Time-Series Data Sharing with Deep Reinforcement Learning
Authors Ecenaz Erdemir, Pier Luigi Dragotti, Deniz Gunduz
Abstract Internet of things (IoT) devices are becoming increasingly popular thanks to many new services and applications they offer. However, in addition to their many benefits, they raise privacy concerns since they share fine-grained time-series user data with untrusted third parties. In this work, we study the privacy-utility trade-off (PUT) in time-series data sharing. Existing approaches to PUT mainly focus on a single data point; however, temporal correlations in time-series data introduce new challenges. Methods that preserve the privacy for the current time may leak significant amount of information at the trace level as the adversary can exploit temporal correlations in a trace. We consider sharing the distorted version of a user’s true data sequence with an untrusted third party. We measure the privacy leakage by the mutual information between the user’s true data sequence and shared version. We consider both instantaneous and average distortion between the two sequences, under a given distortion measure, as the utility loss metric. To tackle the history-dependent mutual information minimization, we reformulate the problem as a Markov decision process (MDP), and solve it using asynchronous actor-critic deep reinforcement learning (RL). We apply our optimal data release policies to location trace privacy scenario, and evaluate the performance of the proposed policy numerically.
Tasks Time Series
Published 2020-03-04
URL https://arxiv.org/abs/2003.02685v1
PDF https://arxiv.org/pdf/2003.02685v1.pdf
PWC https://paperswithcode.com/paper/privacy-aware-time-series-data-sharing-with
Repo
Framework

Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy

Title Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy
Authors Jaejun Yoo, Namhyuk Ahn, Kyung-Ah Sohn
Abstract Data augmentation is an effective way to improve the performance of deep networks. Unfortunately, current methods are mostly developed for high-level vision tasks (e.g., classification) and few are studied for low-level vision tasks (e.g., image restoration). In this paper, we provide a comprehensive analysis of the existing augmentation methods applied to the super-resolution task. We find that the methods discarding or manipulating the pixels or features too much hamper the image restoration, where the spatial relationship is very important. Based on our analyses, we propose CutBlur that cuts a low-resolution patch and pastes it to the corresponding high-resolution image region and vice versa. The key intuition of CutBlur is to enable a model to learn not only “how” but also “where” to super-resolve an image. By doing so, the model can understand “how much”, instead of blindly learning to apply super-resolution to every given pixel. Our method consistently and significantly improves the performance across various scenarios, especially when the model size is big and the data is collected under real-world environments. We also show that our method improves other low-level vision tasks, such as denoising and compression artifact removal.
Tasks Data Augmentation, Denoising, Image Restoration, Image Super-Resolution, Super-Resolution
Published 2020-04-01
URL https://arxiv.org/abs/2004.00448v1
PDF https://arxiv.org/pdf/2004.00448v1.pdf
PWC https://paperswithcode.com/paper/rethinking-data-augmentation-for-image-super
Repo
Framework

Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion

Title Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
Authors Qinqing Zheng, Jinshuo Dong, Qi Long, Weijie J. Su
Abstract Datasets containing sensitive information are often sequentially analyzed by many algorithms. This raises a fundamental question in differential privacy regarding how the overall privacy bound degrades under composition. To address this question, we introduce a family of analytical and sharp privacy bounds under composition using the Edgeworth expansion in the framework of the recently proposed f-differential privacy. In contrast to the existing composition theorems using the central limit theorem, our new privacy bounds under composition gain improved tightness by leveraging the refined approximation accuracy of the Edgeworth expansion. Our approach is easy to implement and computationally efficient for any number of compositions. The superiority of these new bounds is confirmed by an asymptotic error analysis and an application to quantifying the overall privacy guarantees of noisy stochastic gradient descent used in training private deep neural networks.
Tasks
Published 2020-03-10
URL https://arxiv.org/abs/2003.04493v2
PDF https://arxiv.org/pdf/2003.04493v2.pdf
PWC https://paperswithcode.com/paper/sharp-composition-bounds-for-gaussian
Repo
Framework

Parsing Thai Social Data: A New Challenge for Thai NLP

Title Parsing Thai Social Data: A New Challenge for Thai NLP
Authors Sattaya Singkul, Borirat Khampingyot, Nattasit Maharattamalai, Supawat Taerungruang, Tawunrat Chalothorn
Abstract Dependency parsing (DP) is a task that analyzes text for syntactic structure and relationship between words. DP is widely used to improve natural language processing (NLP) applications in many languages such as English. Previous works on DP are generally applicable to formally written languages. However, they do not apply to informal languages such as the ones used in social networks. Therefore, DP has to be researched and explored with such social network data. In this paper, we explore and identify a DP model that is suitable for Thai social network data. After that, we will identify the appropriate linguistic unit as an input. The result showed that, the transition based model called, improve Elkared dependency parser outperform the others at UAS of 81.42%.
Tasks Dependency Parsing
Published 2020-03-06
URL https://arxiv.org/abs/2003.03069v1
PDF https://arxiv.org/pdf/2003.03069v1.pdf
PWC https://paperswithcode.com/paper/parsing-thai-social-data-a-new-challenge-for
Repo
Framework
comments powered by Disqus