April 1, 2020

3062 words 15 mins read

Paper Group ANR 447

Depth Completion using a View Constrained Deep Prior. Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control. End-to-End Models for the Analysis of Pupil Size Variations and Diagnosis of Parkinson’s Disease. Amplifying The Uncanny. Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially …

Depth Completion using a View Constrained Deep Prior


Title	Depth Completion using a View Constrained Deep Prior
Authors	Pallabi Ghosh, Vibhav Vineet, Larry S. Davis, Abhinav Shrivastava, Sudipta Sinha, Neel Joshi
Abstract	Recent work has shown that the structure of convolutional neural networks (CNNs) induces a strong prior that favors natural images. This prior, known as a deep image prior (DIP), is an effective regularizer in inverse problems such as image denoising and inpainting. We extend the DIP concept to apply to depth images. Given color images and noisy and incomplete target depth maps, we optimize a randomly-initialized CNN model to reconstruct an depth map restored by virtue of using the CNN network structure as a prior combined with a view-constrained photo-consistency loss, which is computed using images from a geometrically calibrated camera from nearby viewpoints. We apply this deep depth prior for inpainting and refining incomplete and noisy depth maps within both binocular and multi-view stereo pipelines. Our quantitative and qualitative evaluation shows that our refined depth maps are more accurate and complete, and after fusion, produces dense 3D models of higher quality.
Tasks	Denoising, Depth Completion, Image Denoising
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07791v2
PDF	https://arxiv.org/pdf/2001.07791v2.pdf
PWC	https://paperswithcode.com/paper/deep-depth-prior-for-multi-view-stereo
Repo
Framework

Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control


Title	Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control
Authors	Christian Schroeder de Witt, Bei Peng, Pierre-Alexandre Kamienny, Philip Torr, Wendelin Böhmer, Shimon Whiteson
Abstract	Deep multi-agent reinforcement learning (MARL) holds the promise of automating many real-world cooperative robotic manipulation and transportation tasks. Nevertheless, decentralised cooperative robotic control has received less attention from the deep reinforcement learning community, as compared to single-agent robotics and multi-agent games with discrete actions. To address this gap, this paper introduces Multi-Agent Mujoco, an easily extensible multi-agent benchmark suite for robotic control in continuous action spaces. The benchmark tasks are diverse and admit easily configurable partially observable settings. Inspired by the success of single-agent continuous value-based algorithms in robotic control, we also introduce COMIX, a novel extension to a common discrete action multi-agent $Q$-learning algorithm. We show that COMIX significantly outperforms state-of-the-art MADDPG on a partially observable variant of a popular particle environment and matches or surpasses it on Multi-Agent Mujoco. Thanks to this new benchmark suite and method, we can now pose an interesting question: what is the key to performance in such settings, the use of value-based methods instead of policy gradients, or the factorisation of the joint $Q$-function? To answer this question, we propose a second new method, FacMADDPG, which factors MADDPG’s critic. Experimental results on Multi-Agent Mujoco suggest that factorisation is the key to performance.
Tasks	Multi-agent Reinforcement Learning, Q-Learning
Published	2020-03-14
URL	https://arxiv.org/abs/2003.06709v2
PDF	https://arxiv.org/pdf/2003.06709v2.pdf
PWC	https://paperswithcode.com/paper/deep-multi-agent-reinforcement-learning-for
Repo
Framework

End-to-End Models for the Analysis of Pupil Size Variations and Diagnosis of Parkinson’s Disease


Title	End-to-End Models for the Analysis of Pupil Size Variations and Diagnosis of Parkinson’s Disease
Authors	Dario Zanca, Alessandra Rufa, Andrea Canessa, Silvio Sabatini
Abstract	It is well known that a systematic analysis of the pupil size variations, recorded by means of an eye-tracker, is a rich source of information about a subject’s cognitive state. In this work we present end-to-end models for the diagnosis of Parkinson’s disease (PD) based on the raw pupil size signal. Long-range registration (10 minutes) of the pupil size were collected in scotopic conditions (complete darkness, 0 lux) on 21 healthy subjects and 15 subjects diagnosed with PD. 1-D convolutional neural network models are trained for classification of short-range sequences (10 to 60 seconds of registration). The model provides prediction with high average accuracy on a hold out test set. A temporal analysis of the model performance allowed the characterization of pupil’s size variations in PD and healthy subjects during a resting state. Dataset and codes are released for reproducibility and benchmarking purposes.
Tasks
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02383v1
PDF	https://arxiv.org/pdf/2002.02383v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-models-for-the-analysis-of-pupil
Repo
Framework

Amplifying The Uncanny


Title	Amplifying The Uncanny
Authors	Terence Broad, Frederic Fol Leymarie, Mick Grierson
Abstract	Deep neural networks have become remarkably good at producing realistic deepfakes, images of people that are (to the untrained eye) indistinguishable from real images. These are produced by algorithms that learn to distinguish between real and fake images and are optimised to generate samples that the system deems realistic. This paper, and the resulting series of artworks Being Foiled explore the aesthetic outcome of inverting this process and instead optimising the system to generate images that it sees as being fake. Maximising the unlikelihood of the data and in turn, amplifying the uncanny nature of these machine hallucinations.
Tasks
Published	2020-02-17
URL	https://arxiv.org/abs/2002.06890v1
PDF	https://arxiv.org/pdf/2002.06890v1.pdf
PWC	https://paperswithcode.com/paper/amplifying-the-uncanny
Repo
Framework

Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials


Title	Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials
Authors	Min Li, Zhenglong Zhou, Zhe Wu, Boxin Shi, Changyu Diao, Ping Tan
Abstract	We present a method to capture both 3D shape and spatially varying reflectance with a multi-view photometric stereo (MVPS) technique that works for general isotropic materials. Our algorithm is suitable for perspective cameras and nearby point light sources. Our data capture setup is simple, which consists of only a digital camera, some LED lights, and an optional automatic turntable. From a single viewpoint, we use a set of photometric stereo images to identify surface points with the same distance to the camera. We collect this information from multiple viewpoints and combine it with structure-from-motion to obtain a precise reconstruction of the complete 3D shape. The spatially varying isotropic bidirectional reflectance distribution function (BRDF) is captured by simultaneously inferring a set of basis BRDFs and their mixing weights at each surface point. In experiments, we demonstrate our algorithm with two different setups: a studio setup for highest precision and a desktop setup for best usability. According to our experiments, under the studio setting, the captured shapes are accurate to 0.5 millimeters and the captured reflectance has a relative root-mean-square error (RMSE) of 9%. We also quantitatively evaluate state-of-the-art MVPS on a newly collected benchmark dataset, which is publicly available for inspiring future research.
Tasks
Published	2020-01-18
URL	https://arxiv.org/abs/2001.06659v1
PDF	https://arxiv.org/pdf/2001.06659v1.pdf
PWC	https://paperswithcode.com/paper/multi-view-photometric-stereo-a-robust
Repo
Framework

Urdu-English Machine Transliteration using Neural Networks


Title	Urdu-English Machine Transliteration using Neural Networks
Authors	Usman Mohy ud Din
Abstract	Machine translation has gained much attention in recent years. It is a sub-field of computational linguistic which focus on translating text from one language to other language. Among different translation techniques, neural network currently leading the domain with its capabilities of providing a single large neural network with attention mechanism, sequence-to-sequence and long-short term modelling. Despite significant progress in domain of machine translation, translation of out-of-vocabulary words(OOV) which include technical terms, named-entities, foreign words are still a challenge for current state-of-art translation systems, and this situation becomes even worse while translating between low resource languages or languages having different structures. Due to morphological richness of a language, a word may have different meninges in different context. In such scenarios, translation of word is not only enough in order provide the correct/quality translation. Transliteration is a way to consider the context of word/sentence during translation. For low resource language like Urdu, it is very difficult to have/find parallel corpus for transliteration which is large enough to train the system. In this work, we presented transliteration technique based on Expectation Maximization (EM) which is un-supervised and language independent. Systems learns the pattern and out-of-vocabulary (OOV) words from parallel corpus and there is no need to train it on transliteration corpus explicitly. This approach is tested on three models of statistical machine translation (SMT) which include phrasebased, hierarchical phrase-based and factor based models and two models of neural machine translation which include LSTM and transformer model.
Tasks	Machine Translation, Transliteration
Published	2020-01-12
URL	https://arxiv.org/abs/2001.05296v1
PDF	https://arxiv.org/pdf/2001.05296v1.pdf
PWC	https://paperswithcode.com/paper/urdu-english-machine-transliteration-using
Repo
Framework

Uncertainty in Structured Prediction


Title	Uncertainty in Structured Prediction
Authors	Andrey Malinin, Mark Gales
Abstract	Uncertainty estimation is important for ensuring safety and robustness of AI systems, especially for high-risk applications. While much progress has recently been made in this area, most research has focused on un-structured prediction, such as image classification and regression tasks. However, while task-specific forms of confidence score estimation have been investigated by the speech and machine translation communities, limited work has investigated general uncertainty estimation approaches for structured prediction. Thus, this work aims to investigate uncertainty estimation for structured prediction tasks within a single unified and interpretable probabilistic ensemble-based framework. We consider uncertainty estimation for sequence data at the token-level and complete sequence-level, provide interpretations for, and applications of, various measures of uncertainty and discuss the challenges associated with obtaining them. This work also explores the practical challenges associated with obtaining uncertainty estimates for structured predictions tasks and provides baselines for token-level error detection, sequence-level prediction rejection, and sequence-level out-of-domain input detection using ensembles of auto-regressive transformer models trained on the WMT’14 English-French and WMT’17 English-German translation and LibriSpeech speech recognition datasets.
Tasks	Image Classification, Machine Translation, Speech Recognition, Structured Prediction
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07650v2
PDF	https://arxiv.org/pdf/2002.07650v2.pdf
PWC	https://paperswithcode.com/paper/uncertainty-in-structured-prediction
Repo
Framework

Deep Grouping Model for Unified Perceptual Parsing


Title	Deep Grouping Model for Unified Perceptual Parsing
Authors	Zhiheng Li, Wenxuan Bao, Jiayang Zheng, Chenliang Xu
Abstract	The perceptual-based grouping process produces a hierarchical and compositional image representation that helps both human and machine vision systems recognize heterogeneous visual concepts. Examples can be found in the classical hierarchical superpixel segmentation or image parsing works. However, the grouping process is largely overlooked in modern CNN-based image segmentation networks due to many challenges, including the inherent incompatibility between the grid-shaped CNN feature map and the irregular-shaped perceptual grouping hierarchy. Overcoming these challenges, we propose a deep grouping model (DGM) that tightly marries the two types of representations and defines a bottom-up and a top-down process for feature exchanging. When evaluating the model on the recent Broden+ dataset for the unified perceptual parsing task, it achieves state-of-the-art results while having a small computational overhead compared to other contextual-based segmentation models. Furthermore, the DGM has better interpretability compared with modern CNN methods.
Tasks	Semantic Segmentation
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11647v1
PDF	https://arxiv.org/pdf/2003.11647v1.pdf
PWC	https://paperswithcode.com/paper/deep-grouping-model-for-unified-perceptual
Repo
Framework

New mechanism of combination crossover operators in genetic algorithm for solving the traveling salesman problem


Title	New mechanism of combination crossover operators in genetic algorithm for solving the traveling salesman problem
Authors	Pham Dinh Thanh, Huynh Thi Thanh Binh, Bui Thu Lam
Abstract	Traveling salesman problem (TSP) is a well-known in computing field. There are many researches to improve the genetic algorithm for solving TSP. In this paper, we propose two new crossover operators and new mechanism of combination crossover operators in genetic algorithm for solving TSP. We experimented on TSP instances from TSP-Lib and compared the results of proposed algorithm with genetic algorithm (GA), which used MSCX. Experimental results show that, our proposed algorithm is better than the GA using MSCX on the min, mean cost values.
Tasks
Published	2020-01-14
URL	https://arxiv.org/abs/2001.11590v1
PDF	https://arxiv.org/pdf/2001.11590v1.pdf
PWC	https://paperswithcode.com/paper/new-mechanism-of-combination-crossover
Repo
Framework

Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning


Title	Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning
Authors	Jinhyun So, Basak Guler, A. Salman Avestimehr
Abstract	Federated learning is gaining significant interests as it enables model training over a large volume of data that is distributedly stored over many users, while protecting the privacy of the individual users. However, a major bottleneck in scaling federated learning to a large number of users is the overhead of secure model aggregation across many users. In fact, the overhead of state-of-the-art protocols for secure model aggregation grows quadratically with the number of users. We propose a new scheme, named Turbo-Aggregate, that in a network with $N$ users achieves a secure aggregation overhead of $O(N\log{N})$, as opposed to $O(N^2)$, while tolerating up to a user dropout rate of $50%$. Turbo-Aggregate employs a multi-group circular strategy for efficient model aggregation, and leverages additive secret sharing and novel coding techniques for injecting aggregation redundancy in order to handle user dropouts while guaranteeing user privacy. We experimentally demonstrate that Turbo-Aggregate achieves a total running time that grows almost linear in the number of users, and provides up to $14\times$ speedup over the state-of-the-art schemes with upto $N=200$ users. We also experimentally evaluate the impact of several key network parameters (e.g., user dropout rate, bandwidth, and model size) on the performance of Turbo-Aggregate.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04156v1
PDF	https://arxiv.org/pdf/2002.04156v1.pdf
PWC	https://paperswithcode.com/paper/turbo-aggregate-breaking-the-quadratic
Repo
Framework

Revealing Neural Network Bias to Non-Experts Through Interactive Counterfactual Examples


Title	Revealing Neural Network Bias to Non-Experts Through Interactive Counterfactual Examples
Authors	Chelsea M. Myers, Evan Freed, Luis Fernando Laris Pardo, Anushay Furqan, Sebastian Risi, Jichen Zhu
Abstract	AI algorithms are not immune to biases. Traditionally, non-experts have little control in uncovering potential social bias (e.g., gender bias) in the algorithms that may impact their lives. We present a preliminary design for an interactive visualization tool CEB to reveal biases in a commonly used AI method, Neural Networks (NN). CEB combines counterfactual examples and abstraction of an NN decision process to empower non-experts to detect bias. This paper presents the design of CEB and initial findings of an expert panel (n=6) with AI, HCI, and Social science experts.
Tasks
Published	2020-01-07
URL	https://arxiv.org/abs/2001.02271v2
PDF	https://arxiv.org/pdf/2001.02271v2.pdf
PWC	https://paperswithcode.com/paper/revealing-neural-network-bias-to-non-experts
Repo
Framework

Linear and Fisher Separability of Random Points in the d-dimensional Spherical Layer


Title	Linear and Fisher Separability of Random Points in the d-dimensional Spherical Layer
Authors	Sergey Sidorov, Nikolai Zolotykh
Abstract	Stochastic separation theorems play important role in high-dimensional data analysis and machine learning. It turns out that in high dimension any point of a random set of points can be separated from other points by a hyperplane with high probability even the number of points is exponential in terms of dimension. This and similar facts can be used for constructing correctors for artificial intelligent systems, for determining an intrinsic dimension of data and for explaining various natural intelligence phenomena. In this paper, we refine the bounds for the number of points and for the probability in stochastic separation theorems, thereby strengthening some results obtained by Gorban, Tyukin, Burton, Sidorov, Zolotykh et al. We give and discuss the bounds for linear and Fisher separability, when the points are drawn randomly, independently and uniformly from a d-dimensional spherical layer. These results allow us to better outline the applicability limits of the stochastic separation theorems in the mentioned applications.
Tasks
Published	2020-02-01
URL	https://arxiv.org/abs/2002.01306v1
PDF	https://arxiv.org/pdf/2002.01306v1.pdf
PWC	https://paperswithcode.com/paper/linear-and-fisher-separability-of-random
Repo
Framework

Inferring Individual Level Causal Models from Graph-based Relational Time Series


Title	Inferring Individual Level Causal Models from Graph-based Relational Time Series
Authors	Ryan Rossi, Somdeb Sarkhel, Nesreen Ahmed
Abstract	In this work, we formalize the problem of causal inference over graph-based relational time-series data where each node in the graph has one or more time-series associated to it. We propose causal inference models for this problem that leverage both the graph topology and time-series to accurately estimate local causal effects of nodes. Furthermore, the relational time-series causal inference models are able to estimate local effects for individual nodes by exploiting local node-centric temporal dependencies and topological/structural dependencies. We show that simpler causal models that do not consider the graph topology are recovered as special cases of the proposed relational time-series causal inference model. We describe the conditions under which the resulting estimate can be used to estimate a causal effect, and describe how the Durbin-Wu-Hausman test of specification can be used to test for the consistency of the proposed estimator from data. Empirically, we demonstrate the effectiveness of the causal inference models on both synthetic data with known ground-truth and a large-scale observational relational time-series data set collected from Wikipedia.
Tasks	Causal Inference, Time Series
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05993v3
PDF	https://arxiv.org/pdf/2001.05993v3.pdf
PWC	https://paperswithcode.com/paper/inferring-individual-level-causal-models-from
Repo
Framework

Broad Area Search and Detection of Surface-to-Air Missile Sites Using Spatial Fusion of Component Object Detections from Deep Neural Networks


Title	Broad Area Search and Detection of Surface-to-Air Missile Sites Using Spatial Fusion of Component Object Detections from Deep Neural Networks
Authors	Alan B. Cannaday II, Curt H. Davis, Grant J. Scott, Blake Ruprecht, Derek T. Anderson
Abstract	Here we demonstrate how Deep Neural Network (DNN) detections of multiple constitutive or component objects that are part of a larger, more complex, and encompassing feature can be spatially fused to improve the search, detection, and retrieval (ranking) of the larger complex feature. First, scores computed from a spatial clustering algorithm are normalized to a reference space so that they are independent of image resolution and DNN input chip size. Then, multi-scale DNN detections from various component objects are fused to improve the detection and retrieval of DNN detections of a larger complex feature. We demonstrate the utility of this approach for broad area search and detection of Surface-to-Air Missile (SAM) sites that have a very low occurrence rate (only 16 sites) over a ~90,000 km^2 study area in SE China. The results demonstrate that spatial fusion of multi-scale component-object DNN detections can reduce the detection error rate of SAM Sites by $>$85% while still maintaining a 100% recall. The novel spatial fusion approach demonstrated here can be easily extended to a wide variety of other challenging object search and detection problems in large-scale remote sensing image datasets.
Tasks
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10566v1
PDF	https://arxiv.org/pdf/2003.10566v1.pdf
PWC	https://paperswithcode.com/paper/broad-area-search-and-detection-of-surface-to
Repo
Framework

SPN-CNN: Boosting Sensor-Based Source Camera Attribution With Deep Learning


Title	SPN-CNN: Boosting Sensor-Based Source Camera Attribution With Deep Learning
Authors	Matthias Kirchner, Cameron Johnson
Abstract	We explore means to advance source camera identification based on sensor noise in a data-driven framework. Our focus is on improving the sensor pattern noise (SPN) extraction from a single image at test time. Where existing works suppress nuisance content with denoising filters that are largely agnostic to the specific SPN signal of interest, we demonstrate that a~deep learning approach can yield a more suitable extractor that leads to improved source attribution. A series of extensive experiments on various public datasets confirms the feasibility of our approach and its applicability to image manipulation localization and video source attribution. A critical discussion of potential pitfalls completes the text.
Tasks	Denoising
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02927v1
PDF	https://arxiv.org/pdf/2002.02927v1.pdf
PWC	https://paperswithcode.com/paper/spn-cnn-boosting-sensor-based-source-camera
Repo
Framework