October 21, 2019

2733 words 13 mins read

Paper Group AWR 135

Learning Warped Guidance for Blind Face Restoration. Precision and Recall for Time Series. Gradient and Newton Boosting for Classification and Regression. Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos. On Robust Trimming of Bayesian Network Classifiers. Breaking NLI Systems with Sentences that Require Simple Lexical I …


Title	Learning Warped Guidance for Blind Face Restoration
Authors	Xiaoming Li, Ming Liu, Yuting Ye, Wangmeng Zuo, Liang Lin, Ruigang Yang
Abstract	This paper studies the problem of blind face restoration from an unconstrained blurry, noisy, low-resolution, or compressed image (i.e., degraded observation). For better recovery of fine facial details, we modify the problem setting by taking both the degraded observation and a high-quality guided image of the same identity as input to our guided face restoration network (GFRNet). However, the degraded observation and guided image generally are different in pose, illumination and expression, thereby making plain CNNs (e.g., U-Net) fail to recover fine and identity-aware facial details. To tackle this issue, our GFRNet model includes both a warping subnetwork (WarpNet) and a reconstruction subnetwork (RecNet). The WarpNet is introduced to predict flow field for warping the guided image to correct pose and expression (i.e., warped guidance), while the RecNet takes the degraded observation and warped guidance as input to produce the restoration result. Due to that the ground-truth flow field is unavailable, landmark loss together with total variation regularization are incorporated to guide the learning of WarpNet. Furthermore, to make the model applicable to blind restoration, our GFRNet is trained on the synthetic data with versatile settings on blur kernel, noise level, downsampling scale factor, and JPEG quality factor. Experiments show that our GFRNet not only performs favorably against the state-of-the-art image and face restoration methods, but also generates visually photo-realistic results on real degraded facial images.
Tasks
Published	2018-04-13
URL	http://arxiv.org/abs/1804.04829v2
PDF	http://arxiv.org/pdf/1804.04829v2.pdf
PWC	https://paperswithcode.com/paper/learning-warped-guidance-for-blind-face
Repo	https://github.com/csxmli2016/GFRNet
Framework	pytorch

Precision and Recall for Time Series


Title	Precision and Recall for Time Series
Authors	Nesime Tatbul, Tae Jun Lee, Stan Zdonik, Mejbah Alam, Justin Gottschlich
Abstract	Classical anomaly detection is principally concerned with point-based anomalies, those anomalies that occur at a single point in time. Yet, many real-world anomalies are range-based, meaning they occur over a period of time. Motivated by this observation, we present a new mathematical model to evaluate the accuracy of time series classification algorithms. Our model expands the well-known Precision and Recall metrics to measure ranges, while simultaneously enabling customization support for domain-specific preferences.
Tasks	Anomaly Detection, Time Series, Time Series Classification
Published	2018-03-08
URL	http://arxiv.org/abs/1803.03639v3
PDF	http://arxiv.org/pdf/1803.03639v3.pdf
PWC	https://paperswithcode.com/paper/precision-and-recall-for-time-series
Repo	https://github.com/KurochkinAlexey/TSPrecisionRecall
Framework	none

Gradient and Newton Boosting for Classification and Regression


Title	Gradient and Newton Boosting for Classification and Regression
Authors	Fabio Sigrist
Abstract	Boosting algorithms show high predictive accuracy on a wide array of datasets. To date, the distinction between boosting with either gradient descent or second-order updates is often not made, and it is thus implicitly assumed that the difference is irrelevant. In this article, we present gradient and Newton boosting, as well as a hybrid variant of the two, in a unified framework. We compare theses boosting algorithms with trees as base learners on a large set of regression and classification datasets using various choices of loss functions. Our experiments show that Newton boosting outperforms gradient and hybrid gradient-Newton boosting in terms of predictive accuracy on the majority of datasets. Further, we present empirical evidence that this difference in predictive accuracy is not primarily due to faster convergence of Newton boosting, but rather since Newton boosting often achieves lower test errors while at the same time having lower training losses. In addition, we introduce a novel tuning parameter for tree-based Newton boosting which is interpretable and important for predictive accuracy.
Tasks
Published	2018-08-09
URL	http://arxiv.org/abs/1808.03064v4
PDF	http://arxiv.org/pdf/1808.03064v4.pdf
PWC	https://paperswithcode.com/paper/gradient-and-newton-boosting-for
Repo	https://github.com/fabsig/KTBoost
Framework	none

Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos


Title	Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos
Authors	Ying Tai, Yicong Liang, Xiaoming Liu, Lei Duan, Jilin Li, Chengjie Wang, Feiyue Huang, Yu Chen
Abstract	In recent years, heatmap regression based models have shown their effectiveness in face alignment and pose estimation. However, Conventional Heatmap Regression (CHR) is not accurate nor stable when dealing with high-resolution facial videos, since it finds the maximum activated location in heatmaps which are generated from rounding coordinates, and thus leads to quantization errors when scaling back to the original high-resolution space. In this paper, we propose a Fractional Heatmap Regression (FHR) for high-resolution video-based face alignment. The proposed FHR can accurately estimate the fractional part according to the 2D Gaussian function by sampling three points in heatmaps. To further stabilize the landmarks among continuous video frames while maintaining the precise at the same time, we propose a novel stabilization loss that contains two terms to address time delay and non-smooth issues, respectively. Experiments on 300W, 300-VW and Talking Face datasets clearly demonstrate that the proposed method is more accurate and stable than the state-of-the-art models.
Tasks	Face Alignment, Pose Estimation, Quantization
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00342v2
PDF	http://arxiv.org/pdf/1811.00342v2.pdf
PWC	https://paperswithcode.com/paper/towards-highly-accurate-and-stable-face
Repo	https://github.com/tyshiwo/FHR_alignment
Framework	pytorch

On Robust Trimming of Bayesian Network Classifiers


Title	On Robust Trimming of Bayesian Network Classifiers
Authors	YooJung Choi, Guy Van den Broeck
Abstract	This paper considers the problem of removing costly features from a Bayesian network classifier. We want the classifier to be robust to these changes, and maintain its classification behavior. To this end, we propose a closeness metric between Bayesian classifiers, called the expected classification agreement (ECA). Our corresponding trimming algorithm finds an optimal subset of features and a new classification threshold that maximize the expected agreement, subject to a budgetary constraint. It utilizes new theoretical insights to perform branch-and-bound search in the space of feature sets, while computing bounds on the ECA. Our experiments investigate both the runtime cost of trimming and its effect on the robustness and accuracy of the final classifier.
Tasks
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11243v1
PDF	http://arxiv.org/pdf/1805.11243v1.pdf
PWC	https://paperswithcode.com/paper/on-robust-trimming-of-bayesian-network
Repo	https://github.com/UCLA-StarAI/TrimBN
Framework	none

Breaking NLI Systems with Sentences that Require Simple Lexical Inferences


Title	Breaking NLI Systems with Sentences that Require Simple Lexical Inferences
Authors	Max Glockner, Vered Shwartz, Yoav Goldberg
Abstract	We create a new NLI test set that shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge. The new examples are simpler than the SNLI test set, containing sentences that differ by at most one word from sentences in the training set. Yet, the performance on the new test set is substantially worse across systems trained on SNLI, demonstrating that these systems are limited in their generalization ability, failing to capture many simple inferences.
Tasks
Published	2018-05-06
URL	http://arxiv.org/abs/1805.02266v1
PDF	http://arxiv.org/pdf/1805.02266v1.pdf
PWC	https://paperswithcode.com/paper/breaking-nli-systems-with-sentences-that
Repo	https://github.com/coetaur0/ESIM
Framework	pytorch

Adversarial Noise Layer: Regularize Neural Network By Adding Noise


Title	Adversarial Noise Layer: Regularize Neural Network By Adding Noise
Authors	Zhonghui You, Jinmian Ye, Kunming Li, Zenglin Xu, Ping Wang
Abstract	In this paper, we introduce a novel regularization method called Adversarial Noise Layer (ANL) and its efficient version called Class Adversarial Noise Layer (CANL), which are able to significantly improve CNN’s generalization ability by adding carefully crafted noise into the intermediate layer activations. ANL and CANL can be easily implemented and integrated with most of the mainstream CNN-based models. We compared the effects of the different types of noise and visually demonstrate that our proposed adversarial noise instruct CNN models to learn to extract cleaner feature maps, which further reduce the risk of over-fitting. We also conclude that models trained with ANL or CANL are more robust to the adversarial examples generated by FGSM than the traditional adversarial training approaches.
Tasks
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08000v2
PDF	http://arxiv.org/pdf/1805.08000v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-noise-layer-regularize-neural
Repo	https://github.com/youzhonghui/ANL
Framework	pytorch

Been There, Done That: Meta-Learning with Episodic Recall


Title	Been There, Done That: Meta-Learning with Episodic Recall
Authors	Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew Botvinick
Abstract	Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discovered solutions. We propose a formalism for generating open-ended yet repetitious environments, then develop a meta-learning architecture for solving these environments. This architecture melds the standard LSTM working memory with a differentiable neural episodic memory. We explore the capabilities of agents with this episodic LSTM in five meta-learning environments with reoccurring tasks, ranging from bandits to navigation and stochastic sequential decision problems.
Tasks	Meta-Learning
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09692v2
PDF	http://arxiv.org/pdf/1805.09692v2.pdf
PWC	https://paperswithcode.com/paper/been-there-done-that-meta-learning-with
Repo	https://github.com/qihongl/dlstm-demo
Framework	pytorch

Some Considerations on Learning to Explore via Meta-Reinforcement Learning


Title	Some Considerations on Learning to Explore via Meta-Reinforcement Learning
Authors	Bradly C. Stadie, Ge Yang, Rein Houthooft, Xi Chen, Yan Duan, Yuhuai Wu, Pieter Abbeel, Ilya Sutskever
Abstract	We consider the problem of exploration in meta reinforcement learning. Two new meta reinforcement learning algorithms are suggested: E-MAML and E-$\text{RL}^2$. Results are presented on a novel environment we call `Krazy World’ and a set of maze environments. We show E-MAML and E-$\text{RL}^2$ deliver better performance on tasks where exploration is important. \|
Tasks
Published	2018-03-03
URL	http://arxiv.org/abs/1803.01118v2
PDF	http://arxiv.org/pdf/1803.01118v2.pdf
PWC	https://paperswithcode.com/paper/some-considerations-on-learning-to-explore
Repo	https://github.com/clrrrr/promp_plus
Framework	none

Anomaly Detection via Graphical Lasso


Title	Anomaly Detection via Graphical Lasso
Authors	Haitao Liu, Randy C. Paffenroth, Jian Zou, Chong Zhou
Abstract	Anomalies and outliers are common in real-world data, and they can arise from many sources, such as sensor faults. Accordingly, anomaly detection is important both for analyzing the anomalies themselves and for cleaning the data for further analysis of its ambient structure. Nonetheless, a precise definition of anomalies is important for automated detection and herein we approach such problems from the perspective of detecting sparse latent effects embedded in large collections of noisy data. Standard Graphical Lasso-based techniques can identify the conditional dependency structure of a collection of random variables based on their sample covariance matrix. However, classic Graphical Lasso is sensitive to outliers in the sample covariance matrix. In particular, several outliers in a sample covariance matrix can destroy the sparsity of its inverse. Accordingly, we propose a novel optimization problem that is similar in spirit to Robust Principal Component Analysis (RPCA) and splits the sample covariance matrix $M$ into two parts, $M=F+S$, where $F$ is the cleaned sample covariance whose inverse is sparse and computable by Graphical Lasso, and $S$ contains the outliers in $M$. We accomplish this decomposition by adding an additional $ \ell_1$ penalty to classic Graphical Lasso, and name it “Robust Graphical Lasso (Rglasso)". Moreover, we propose an Alternating Direction Method of Multipliers (ADMM) solution to the optimization problem which scales to large numbers of unknowns. We evaluate our algorithm on both real and synthetic datasets, obtaining interpretable results and outperforming the standard robust Minimum Covariance Determinant (MCD) method and Robust Principal Component Analysis (RPCA) regarding both accuracy and speed.
Tasks	Anomaly Detection
Published	2018-11-10
URL	http://arxiv.org/abs/1811.04277v1
PDF	http://arxiv.org/pdf/1811.04277v1.pdf
PWC	https://paperswithcode.com/paper/anomaly-detection-via-graphical-lasso
Repo	https://github.com/lht1949/AnomalyDetection
Framework	none

TrolleyMod v1.0: An Open-Source Simulation and Data-Collection Platform for Ethical Decision Making in Autonomous Vehicles


Title	TrolleyMod v1.0: An Open-Source Simulation and Data-Collection Platform for Ethical Decision Making in Autonomous Vehicles
Authors	Vahid Behzadan, James Minton, Arslan Munir
Abstract	This paper presents TrolleyMod v1.0, an open-source platform based on the CARLA simulator for the collection of ethical decision-making data for autonomous vehicles. This platform is designed to facilitate experiments aiming to observe and record human decisions and actions in high-fidelity simulations of ethical dilemmas that occur in the context of driving. Targeting experiments in the class of trolley problems, TrolleyMod provides a seamless approach to creating new experimental settings and environments with the realistic physics-engine and the high-quality graphical capabilities of CARLA and the Unreal Engine. Also, TrolleyMod provides a straightforward interface between the CARLA environment and Python to enable the implementation of custom controllers, such as deep reinforcement learning agents. The results of such experiments can be used for sociological analyses, as well as the training and tuning of value-aligned autonomous vehicles based on social values that are inferred from observations.
Tasks	Autonomous Vehicles, Decision Making
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05594v1
PDF	http://arxiv.org/pdf/1811.05594v1.pdf
PWC	https://paperswithcode.com/paper/trolleymod-v10-an-open-source-simulation-and
Repo	https://github.com/zminton/TrolleyMod
Framework	none

Pythia v0.1: the Winning Entry to the VQA Challenge 2018


Title	Pythia v0.1: the Winning Entry to the VQA Challenge 2018
Authors	Yu Jiang, Vivek Natarajan, Xinlei Chen, Marcus Rohrbach, Dhruv Batra, Devi Parikh
Abstract	This document describes Pythia v0.1, the winning entry from Facebook AI Research (FAIR)‘s A-STAR team to the VQA Challenge 2018. Our starting point is a modular re-implementation of the bottom-up top-down (up-down) model. We demonstrate that by making subtle but important changes to the model architecture and the learning rate schedule, fine-tuning image features, and adding data augmentation, we can significantly improve the performance of the up-down model on VQA v2.0 dataset – from 65.67% to 70.22%. Furthermore, by using a diverse ensemble of models trained with different features and on different datasets, we are able to significantly improve over the ‘standard’ way of ensembling (i.e. same model with different random seeds) by 1.31%. Overall, we achieve 72.27% on the test-std split of the VQA v2.0 dataset. Our code in its entirety (training, evaluation, data-augmentation, ensembling) and pre-trained models are publicly available at: https://github.com/facebookresearch/pythia
Tasks	Data Augmentation, Visual Question Answering
Published	2018-07-26
URL	http://arxiv.org/abs/1807.09956v2
PDF	http://arxiv.org/pdf/1807.09956v2.pdf
PWC	https://paperswithcode.com/paper/pythia-v01-the-winning-entry-to-the-vqa
Repo	https://github.com/songhe17/pythia-clone
Framework	pytorch

Semi-supervised User Geolocation via Graph Convolutional Networks


Title	Semi-supervised User Geolocation via Graph Convolutional Networks
Authors	Afshin Rahimi, Trevor Cohn, Timothy Baldwin
Abstract	Social media user geolocation is vital to many applications such as event detection. In this paper, we propose GCN, a multiview geolocation model based on Graph Convolutional Networks, that uses both text and network context. We compare GCN to the state-of-the-art, and to two baselines we propose, and show that our model achieves or is competitive with the state- of-the-art over three benchmark geolocation datasets when sufficient supervision is available. We also evaluate GCN under a minimal supervision scenario, and show it outperforms baselines. We find that highway network gates are essential for controlling the amount of useful neighbourhood expansion in GCN.
Tasks
Published	2018-04-22
URL	http://arxiv.org/abs/1804.08049v4
PDF	http://arxiv.org/pdf/1804.08049v4.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-user-geolocation-via-graph
Repo	https://github.com/afshinrahimi/geographconv
Framework	none

End-to-End Reinforcement Learning for Automatic Taxonomy Induction


Title	End-to-End Reinforcement Learning for Automatic Taxonomy Induction
Authors	Yuning Mao, Xiang Ren, Jiaming Shen, Xiaotao Gu, Jiawei Han
Abstract	We present a novel end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms. While prior methods treat the problem as a two-phase task (i.e., detecting hypernymy pairs followed by organizing these pairs into a tree-structured hierarchy), we argue that such two-phase methods may suffer from error propagation, and cannot effectively optimize metrics that capture the holistic structure of a taxonomy. In our approach, the representations of term pairs are learned using multiple sources of information and used to determine \textit{which} term to select and \textit{where} to place it on the taxonomy via a policy network. All components are trained in an end-to-end manner with cumulative rewards, measured by a holistic tree metric over the training taxonomies. Experiments on two public datasets of different domains show that our approach outperforms prior state-of-the-art taxonomy induction methods up to 19.6% on ancestor F1.
Tasks
Published	2018-05-10
URL	http://arxiv.org/abs/1805.04044v1
PDF	http://arxiv.org/pdf/1805.04044v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-reinforcement-learning-for
Repo	https://github.com/morningmoni/TaxoRL
Framework	none

Learning from a Handful Volumes: MRI Resolution Enhancement with Volumetric Super-Resolution Forests


Title	Learning from a Handful Volumes: MRI Resolution Enhancement with Volumetric Super-Resolution Forests
Authors	Aline Sindel, Katharina Breininger, Johannes Käßer, Andreas Hess, Andreas Maier, Thomas Köhler
Abstract	Magnetic resonance imaging (MRI) enables 3-D imaging of anatomical structures. However, the acquisition of MR volumes with high spatial resolution leads to long scan times. To this end, we propose volumetric super-resolution forests (VSRF) to enhance MRI resolution retrospectively. Our method learns a locally linear mapping between low-resolution and high-resolution volumetric image patches by employing random forest regression. We customize features suitable for volumetric MRI to train the random forest and propose a median tree ensemble for robust regression. VSRF outperforms state-of-the-art example-based super-resolution in term of image quality and efficiency for model training and inference in different MRI datasets. It is also superior to unsupervised methods with just a handful or even a single volume to assemble training data.
Tasks	Image Super-Resolution, Super-Resolution
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05518v1
PDF	http://arxiv.org/pdf/1802.05518v1.pdf
PWC	https://paperswithcode.com/paper/learning-from-a-handful-volumes-mri
Repo	https://github.com/asindel/VSRF
Framework	none