January 26, 2020

3015 words 15 mins read

Paper Group ANR 1553

Improved PAC-Bayesian Bounds for Linear Regression. Reinforcement Learning with Convolutional Reservoir Computing. Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data. Fast Portrait Segmentation with extremely light-weight network. The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods. Attention …

Improved PAC-Bayesian Bounds for Linear Regression


Title	Improved PAC-Bayesian Bounds for Linear Regression
Authors	Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain, Mihaly Petreczky
Abstract	In this paper, we improve the PAC-Bayesian error bound for linear regression derived in Germain et al. [10]. The improvements are twofold. First, the proposed error bound is tighter, and converges to the generalization loss with a well-chosen temperature parameter. Second, the error bound also holds for training data that are not independently sampled. In particular, the error bound applies to certain time series generated by well-known classes of dynamical models, such as ARX models.
Tasks	Time Series
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03036v1
PDF	https://arxiv.org/pdf/1912.03036v1.pdf
PWC	https://paperswithcode.com/paper/improved-pac-bayesian-bounds-for-linear
Repo
Framework

Reinforcement Learning with Convolutional Reservoir Computing


Title	Reinforcement Learning with Convolutional Reservoir Computing
Authors	Hanten Chang, Katsuya Futagami
Abstract	Recently, reinforcement learning models have achieved great success, mastering complex tasks such as Go and other games with higher scores than human players. Many of these models store considerable data on the tasks and achieve high performance by extracting visual and time-series features using convolutional neural networks (CNNs) and recurrent neural networks, respectively. However, these networks have very high computational costs because they need to be trained by repeatedly using the stored data. In this study, we propose a novel practical approach called reinforcement learning with convolutional reservoir computing (RCRC) model. The RCRC model uses a fixed random-weight CNN and a reservoir computing model to extract visual and time-series features. Using these extracted features, it decides actions with an evolution strategy method. Thereby, the RCRC model has several desirable features: (1) there is no need to train the feature extractor, (2) there is no need to store training data, (3) it can take a wide range of actions, and (4) there is only a single task-dependent weight parameter to be trained. Furthermore, we show the RCRC model can solve multiple reinforcement learning tasks with a completely identical feature extractor.
Tasks	Time Series
Published	2019-12-05
URL	https://arxiv.org/abs/1912.04161v1
PDF	https://arxiv.org/pdf/1912.04161v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-with-convolutional
Repo
Framework

Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data


Title	Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data
Authors	Stefan Oehmcke, Christoffer Thrysøe, Andreas Borgstad, Marcos Antonio Vaz Salles, Martin Brandt, Fabian Gieseke
Abstract	Massive amounts of satellite data have been gathered over time, holding the potential to unveil a spatiotemporal chronicle of the surface of Earth. These data allow scientists to investigate various important issues, such as land use changes, on a global scale. However, not all land-use phenomena are equally visible on satellite imagery. In particular, the creation of an inventory of the planet’s road infrastructure remains a challenge, despite being crucial to analyze urbanization patterns and their impact. Towards this end, this work advances data-driven approaches for the automatic identification of roads based on open satellite data. Given the typical resolutions of these historical satellite data, we observe that there is inherent variation in the visibility of different road types. Based on this observation, we propose two deep learning frameworks that extend state-of-the-art deep learning methods by formalizing road detection as an ordinal classification task. In contrast to related schemes, one of the two models also resorts to satellite time series data that are potentially affected by missing data and cloud occlusion. Taking these time series data into account eliminates the need to manually curate datasets of high-quality image tiles, substantially simplifying the application of such models on a global scale. We evaluate our approaches on a dataset that is based on Sentinel~2 satellite imagery and OpenStreetMap vector data. Our results indicate that the proposed models can successfully identify large and medium-sized roads. We also discuss opportunities and challenges related to the detection of roads and other infrastructure on a global scale.
Tasks	Time Series
Published	2019-12-04
URL	https://arxiv.org/abs/1912.05026v1
PDF	https://arxiv.org/pdf/1912.05026v1.pdf
PWC	https://paperswithcode.com/paper/detecting-hardly-visible-roads-in-low
Repo
Framework

Fast Portrait Segmentation with extremely light-weight network


Title	Fast Portrait Segmentation with extremely light-weight network
Authors	Yuezun Li, Ao Luo, Siwei Lyu
Abstract	In this paper, we describe a fast and light-weight portrait segmentation method based on a new {\em extremely light-weight backbone} (ELB) architecture. The core element of ELB is a {\em bottleneck-based factorized block} (BFB) that has much fewer parameters than existing alternatives while keeping good learning capacity. Consequently, the ELB-based portrait segmentation method can run faster (263.2FPS) than the existing methods yet retaining the competitive accuracy performance with state-of-the-arts. Experiments conducted on two benchmark datasets demonstrate the effectiveness and efficiency of our method.
Tasks
Published	2019-10-19
URL	https://arxiv.org/abs/1910.08695v3
PDF	https://arxiv.org/pdf/1910.08695v3.pdf
PWC	https://paperswithcode.com/paper/fast-and-light-weight-portrait-segmentation
Repo
Framework

The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods


Title	The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods
Authors	Johannes Leuschner, Maximilian Schmidt, Daniel Otero Baguer, Peter Maaß
Abstract	Deep Learning approaches for solving Inverse Problems in imaging have become very effective and are demonstrated to be quite competitive in the field. Comparing these approaches is a challenging task since they highly rely on the data and the setup that is used for training. We provide a public dataset of computed tomography images and simulated low-dose measurements suitable for training this kind of methods. With the LoDoPaB-CT Dataset we aim to create a benchmark that allows for a fair comparison. It contains over 40,000 scan slices from around 800 patients selected from the LIDC/IDRI Database. In this paper we describe how we processed the original slices and how we simulated the measurements. We also include first baseline results.
Tasks
Published	2019-10-01
URL	https://arxiv.org/abs/1910.01113v1
PDF	https://arxiv.org/pdf/1910.01113v1.pdf
PWC	https://paperswithcode.com/paper/the-lodopab-ct-dataset-a-benchmark-dataset
Repo
Framework

Attention for Inference Compilation


Title	Attention for Inference Compilation
Authors	William Harvey, Andreas Munk, Atılım Güneş Baydin, Alexander Bergholm, Frank Wood
Abstract	We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation of inference compilation (IC) which leverages deep neural networks to approximate a posterior distribution over latent variables in a probabilistic program. A challenge with existing IC network architectures is that they can fail to model long-range dependencies between latent variables. To address this, we introduce an attention mechanism that attends to the most salient variables previously sampled in the execution of a probabilistic program. We demonstrate that the addition of attention allows the proposal distributions to better match the true posterior, enhancing inference about latent variables in simulators.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11961v1
PDF	https://arxiv.org/pdf/1910.11961v1.pdf
PWC	https://paperswithcode.com/paper/attention-for-inference-compilation
Repo
Framework

Deep Discriminative Fine-Tuning for Cancer Type Classification


Title	Deep Discriminative Fine-Tuning for Cancer Type Classification
Authors	Alena Harley
Abstract	Determining the primary site of origin for metastatic tumors is one of the open problems in cancer care because the efficacy of treatment often depends on the cancer tissue of origin. Classification methods that can leverage tumor genomic data and predict the site of origin are therefore of great value. Because tumor DNA point mutation data is very sparse, only limited accuracy (64.5% for 12 tumor classes) was previously demonstrated by methods that rely on point mutations as features (1). Tumor classification accuracy can be greatly improved (to over 90% for 33 classes) by relying on gene expression data (2). However, this additional data is often not readily available in clinical setting, because point mutations are better profiled and targeted by clinical mutational profiling. Here we sought to develop an accurate deep transfer learning and fine-tuning method for tumor sub-type classification, where predicted class is indicative of the primary site of origin. Our method significantly outperforms the state-of-the-art for tumor classification using DNA point mutations, reducing the error by more than 30% at the same time discriminating over many more classes on The Cancer Genome Atlas (TCGA) dataset. Using our method, we achieve state-of-the-art tumor type classification accuracy of 78.3% for 29 tumor classes relying on DNA point mutations in the tumor only.
Tasks	Transfer Learning
Published	2019-11-15
URL	https://arxiv.org/abs/1911.07654v1
PDF	https://arxiv.org/pdf/1911.07654v1.pdf
PWC	https://paperswithcode.com/paper/deep-discriminative-fine-tuning-for-cancer
Repo
Framework

Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes


Title	Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes
Authors	Hao Yang, Hao Wu, Hao Chen
Abstract	Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost. Weakly-supervised methods, on the other hand, only require image-level labels for training, but the performance is far below their fully-supervised counterparts. In this paper, we propose a semi-supervised large scale fine-grained detection method, which only needs bounding box annotations of a smaller number of coarse-grained classes and image-level labels of large scale fine-grained classes, and can detect all classes at nearly fully-supervised accuracy. We achieve this by utilizing the correlations between coarse-grained and fine-grained classes with shared backbone, soft-attention based proposal re-ranking, and a dual-level memory module. Experiment results show that our methods can achieve close accuracy on object detection to state-of-the-art fully-supervised methods on two large scale datasets, ImageNet and OpenImages, with only a small fraction of fully annotated classes.
Tasks	Object Detection
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05217v1
PDF	https://arxiv.org/pdf/1908.05217v1.pdf
PWC	https://paperswithcode.com/paper/detecting-11k-classes-large-scale-object
Repo
Framework

Fake News Detection using Stance Classification: A Survey


Title	Fake News Detection using Stance Classification: A Survey
Authors	Anders Edelbo Lillie, Emil Refsgaard Middelboe
Abstract	This paper surveys and presents recent academic work carried out within the field of stance classification and fake news detection. Echo chambers and the model organism problem are examples that pose challenges to acquire data with high quality, due to opinions being polarised in microblogs. Nevertheless it is shown that several machine learning approaches achieve promising results in classifying stance. Some use crowd stance for fake news detection, such as the approach in [Dungs et al., 2018] using Hidden Markov Models. Furthermore feature engineering have significant importance in several approaches, which is shown in [Aker et al., 2017]. This paper additionally includes a proposal of a system implementation based on the presented survey.
Tasks	Fake News Detection, Feature Engineering
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00181v1
PDF	https://arxiv.org/pdf/1907.00181v1.pdf
PWC	https://paperswithcode.com/paper/fake-news-detection-using-stance
Repo
Framework

Privacy-Preserving Multi-Party Contextual Bandits


Title	Privacy-Preserving Multi-Party Contextual Bandits
Authors	Awni Hannun, Brian Knott, Shubho Sengupta, Laurens van der Maaten
Abstract	Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly used to solve recommendation or ranking problems. This paper considers a learning setting in which multiple parties aim to train a contextual bandit together in a private way: the parties aim to maximize the total reward but do not want to share any of the relevant information they possess with the other parties. Specifically, multiple parties have access to (different) features that may benefit the learner but that cannot be shared with other parties. One of the parties pulls the arm but other parties may not learn which arm was pulled. One party receives the reward but the other parties may not learn the reward value. This paper develops a privacy-preserving multi-party contextual bandit for this learning setting by combining secure multi-party computation with a differentially private mechanism based on epsilon-greedy exploration.
Tasks	Multi-Armed Bandits
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05299v3
PDF	https://arxiv.org/pdf/1910.05299v3.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-contextual-bandits
Repo
Framework

Estimating Chlorophyll a Concentrations of Several Inland Waters with Hyperspectral Data and Machine Learning Models


Title	Estimating Chlorophyll a Concentrations of Several Inland Waters with Hyperspectral Data and Machine Learning Models
Authors	Philipp M. Maier, Sina Keller
Abstract	Water is a key component of life, the natural environment and human health. For monitoring the conditions of a water body, the chlorophyll a concentration can serve as a proxy for nutrients and oxygen supply. In situ measurements of water quality parameters are often time-consuming, expensive and limited in areal validity. Therefore, we apply remote sensing techniques. During field campaigns, we collected hyperspectral data with a spectrometer and in situ measured chlorophyll a concentrations of 13 inland water bodies with different spectral characteristics. One objective of this study is to estimate chlorophyll a concentrations of these inland waters by applying three machine learning regression models: Random Forest, Support Vector Machine and an Artificial Neural Network. Additionally, we simulate four different hyperspectral resolutions of the spectrometer data to investigate the effects on the estimation performance. Furthermore, the application of first order derivatives of the spectra is evaluated in turn to the regression performance. This study reveals the potential of combining machine learning approaches and remote sensing data for inland waters. Each machine learning model achieves an R2-score between 80 % to 90 % for the regression on chlorophyll a concentrations. The random forest model benefits clearly from the applied derivatives of the spectra. In further studies, we will focus on the application of machine learning models on spectral satellite data to enhance the area-wide estimation of chlorophyll a concentration for inland waters.
Tasks
Published	2019-04-03
URL	http://arxiv.org/abs/1904.02052v1
PDF	http://arxiv.org/pdf/1904.02052v1.pdf
PWC	https://paperswithcode.com/paper/estimating-chlorophyll-a-concentrations-of
Repo
Framework

Deep Multi-task Prediction of Lung Cancer and Cancer-free Progression from Censored Heterogenous Clinical Imaging


Title	Deep Multi-task Prediction of Lung Cancer and Cancer-free Progression from Censored Heterogenous Clinical Imaging
Authors	Riqiang Gao, Lingfeng Li, Yucheng Tang, Sanja L. Antic, Alexis B. Paulson, Yuankai Huo, Kim L. Sandler, Pierre P. Massion, Bennett A. Landman
Abstract	Annual low dose computed tomography (CT) lung screening is currently advised for individuals at high risk of lung cancer (e.g., heavy smokers between 55 and 80 years old). The recommended screening practice significantly reduces all-cause mortality, but the vast majority of screening results are negative for cancer. If patients at very low risk could be identified based on individualized, image-based biomarkers, the health care resources could be more efficiently allocated to higher risk patients and reduce overall exposure to ionizing radiation. In this work, we propose a multi-task (diagnosis and prognosis) deep convolutional neural network to improve the diagnostic accuracy over a baseline model while simultaneously estimating a personalized cancer-free progression time (CFPT). A novel Censored Regression Loss (CRL) is proposed to perform weakly supervised regression so that even single negative screening scans can provide small incremental value. Herein, we study 2287 scans from 1433 de-identified patients from the Vanderbilt Lung Screening Program (VLSP) and Molecular Characterization Laboratories (MCL) cohorts. Using five-fold cross-validation, we train a 3D attention-based network under two scenarios: (1) single-task learning with only classification, and (2) multi-task learning with both classification and regression. The single-task learning leads to a higher AUC compared with the Kaggle challenge winner pre-trained model (0.878 v. 0.856), and multi-task learning significantly improves the single-task one (AUC 0.895, p<0.01, McNemar test). In summary, the image-based predicted CFPT can be used in follow-up year lung cancer prediction and data assessment.
Tasks	Computed Tomography (CT), Multi-Task Learning
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05115v2
PDF	https://arxiv.org/pdf/1911.05115v2.pdf
PWC	https://paperswithcode.com/paper/deep-multi-task-prediction-of-lung-cancer-and
Repo
Framework

Cycle-Consistent Adversarial Networks for Realistic Pervasive Change Generation in Remote Sensing Imagery


Title	Cycle-Consistent Adversarial Networks for Realistic Pervasive Change Generation in Remote Sensing Imagery
Authors	Christopher X. Ren, Amanda Ziemann, Alice M. S. Durieux, James Theiler
Abstract	This paper introduces a new method of generating realistic pervasive changes in the context of evaluating the effectiveness of change detection algorithms in controlled settings. The method, a cycle-consistent adversarial network (CycleGAN), requires low quantities of training data to generate realistic changes. Here we show an application of CycleGAN in creating realistic snow-covered scenes of multispectral Sentinel-2 imagery, and demonstrate how these images can be used as a test bed for anomalous change detection algorithms.
Tasks
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12546v2
PDF	https://arxiv.org/pdf/1911.12546v2.pdf
PWC	https://paperswithcode.com/paper/cycle-consistent-adversarial-networks-for
Repo
Framework

Dynamic Curriculum Learning for Imbalanced Data Classification


Title	Dynamic Curriculum Learning for Imbalanced Data Classification
Authors	Yiru Wang, Weihao Gan, Jie Yang, Wei Wu, Junjie Yan
Abstract	Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system. To address this problem, we propose a unified framework called Dynamic Curriculum Learning (DCL) to online adaptively adjust the sampling strategy and loss learning in single batch, which resulting in better generalization and discrimination. Inspired by the curriculum learning, DCL consists of two level curriculum schedulers: (1) sampling scheduler not only manages the data distribution from imbalanced to balanced but also from easy to hard; (2) loss scheduler controls the learning importance between classification and metric learning loss. Learning from these two schedulers, we demonstrate our DCL framework with the new state-of-the-art performance on the widely used face attribute dataset CelebA and pedestrian attribute dataset RAP.
Tasks	Metric Learning
Published	2019-01-21
URL	https://arxiv.org/abs/1901.06783v2
PDF	https://arxiv.org/pdf/1901.06783v2.pdf
PWC	https://paperswithcode.com/paper/dynamic-curriculum-learning-for-imbalanced
Repo
Framework

AutoML for Contextual Bandits


Title	AutoML for Contextual Bandits
Authors	Praneet Dutta, Man Kit, Cheuk, Jonathan S Kim, Massimo Mascaro
Abstract	Contextual Bandits is one of the widely popular techniques used in applications such as personalization, recommendation systems, mobile health, causal marketing etc . As a dynamic approach, it can be more efficient than standard A/B testing in minimizing regret. We propose an end to end automated meta-learning pipeline to approximate the optimal Q function for contextual bandits problems. We see that our model is able to perform much better than random exploration, being more regret efficient and able to converge with a limited number of samples, while remaining very general and easy to use due to the meta-learning approach. We used a linearly annealed e-greedy exploration policy to define the exploration vs exploitation schedule. We tested the system on a synthetic environment to characterize it fully and we evaluated it on some open source datasets to benchmark against prior work. We see that our model outperforms or performs comparatively to other models while requiring no tuning nor feature engineering.
Tasks	AutoML, Feature Engineering, Meta-Learning, Multi-Armed Bandits, Recommendation Systems
Published	2019-09-07
URL	https://arxiv.org/abs/1909.03212v1
PDF	https://arxiv.org/pdf/1909.03212v1.pdf
PWC	https://paperswithcode.com/paper/automl-for-contextual-bandits
Repo
Framework