April 2, 2020

3133 words 15 mins read

Paper Group ANR 324

ADRN: Attention-based Deep Residual Network for Hyperspectral Image Denoising. Domain Adaptive Adversarial Learning Based on Physics Model Feedback for Underwater Image Enhancement. Algorithms for Optimizing Fleet Scheduling of Air Ambulances. Indexical Cities: Articulating Personal Models of Urban Preference with Geotagged Data. A Thorough Compari …

ADRN: Attention-based Deep Residual Network for Hyperspectral Image Denoising


Title	ADRN: Attention-based Deep Residual Network for Hyperspectral Image Denoising
Authors	Yongsen Zhao, Deming Zhai, Junjun Jiang, Xianming Liu
Abstract	Hyperspectral image (HSI) denoising is of crucial importance for many subsequent applications, such as HSI classification and interpretation. In this paper, we propose an attention-based deep residual network to directly learn a mapping from noisy HSI to the clean one. To jointly utilize the spatial-spectral information, the current band and its $K$ adjacent bands are simultaneously exploited as the input. Then, we adopt convolution layer with different filter sizes to fuse the multi-scale feature, and use shortcut connection to incorporate the multi-level information for better noise removal. In addition, the channel attention mechanism is employed to make the network concentrate on the most relevant auxiliary information and features that are beneficial to the denoising process best. To ease the training procedure, we reconstruct the output through a residual mode rather than a straightforward prediction. Experimental results demonstrate that our proposed ADRN scheme outperforms the state-of-the-art methods both in quantitative and visual evaluations.
Tasks	Denoising, Image Denoising
Published	2020-03-04
URL	https://arxiv.org/abs/2003.01947v1
PDF	https://arxiv.org/pdf/2003.01947v1.pdf
PWC	https://paperswithcode.com/paper/adrn-attention-based-deep-residual-network
Repo
Framework

Domain Adaptive Adversarial Learning Based on Physics Model Feedback for Underwater Image Enhancement


Title	Domain Adaptive Adversarial Learning Based on Physics Model Feedback for Underwater Image Enhancement
Authors	Yuan Zhou, Kangming Yan
Abstract	Owing to refraction, absorption, and scattering of light by suspended particles in water, raw underwater images suffer from low contrast, blurred details, and color distortion. These characteristics can significantly interfere with the visibility of underwater images and the result of visual tasks, such as segmentation and tracking. To address this problem, we propose a new robust adversarial learning framework via physics model based feedback control and domain adaptation mechanism for enhancing underwater images to get realistic results. A new method for simulating underwater-like training dataset from RGB-D data by underwater image formation model is proposed. Upon the synthetic dataset, a novel enhancement framework, which introduces a domain adaptive mechanism as well as a physics model constraint feedback control, is trained to enhance the underwater scenes. Final enhanced results on synthetic and real underwater images demonstrate the superiority of the proposed method, which outperforms nondeep and deep learning methods in both qualitative and quantitative evaluations. Furthermore, we perform an ablation study to show the contributions of each component we proposed.
Tasks	Domain Adaptation, Image Enhancement
Published	2020-02-20
URL	https://arxiv.org/abs/2002.09315v1
PDF	https://arxiv.org/pdf/2002.09315v1.pdf
PWC	https://paperswithcode.com/paper/domain-adaptive-adversarial-learning-based-on
Repo
Framework

Algorithms for Optimizing Fleet Scheduling of Air Ambulances


Title	Algorithms for Optimizing Fleet Scheduling of Air Ambulances
Authors	Joseph Tassone, Salimur Choudhury
Abstract	Proper scheduling of air assets can be the difference between life and death for a patient. While poor scheduling can be incredibly problematic during hospital transfers, it can be potentially catastrophic in the case of a disaster. These issues are amplified in the case of an air emergency medical service (EMS) system where populations are dispersed, and resources are limited. There are exact methodologies existing for scheduling missions, although actual calculation times can be quite significant given a large enough problem space. For this research, known coordinates of air and health facilities were used in conjunction with a formulated integer linear programming model. This was the programmed through Gurobi so that performance could be compared against custom algorithmic solutions. Two methods were developed, one based on neighbourhood search and the other on Tabu search. While both were able to achieve results quite close to the Gurobi solution, the Tabu search outperformed the former algorithm. Additionally, it was able to do so in a greatly decreased time, with Gurobi actually being unable to resolve to optimal in larger examples. Parallel variations were also developed with the compute unified device architecture (CUDA), though did not improve the timing given the smaller sample size.
Tasks
Published	2020-02-25
URL	https://arxiv.org/abs/2002.11710v1
PDF	https://arxiv.org/pdf/2002.11710v1.pdf
PWC	https://paperswithcode.com/paper/algorithms-for-optimizing-fleet-scheduling-of
Repo
Framework

Indexical Cities: Articulating Personal Models of Urban Preference with Geotagged Data


Title	Indexical Cities: Articulating Personal Models of Urban Preference with Geotagged Data
Authors	Diana Alvarez-Marin, Karla Saldana Ochoa
Abstract	How to assess the potential of liking a city or a neighborhood before ever having been there. The concept of urban quality has until now pertained to global city ranking, where cities are evaluated under a grid of given parameters, or either to empirical and sociological approaches, often constrained by the amount of available information. Using state of the art machine learning techniques and thousands of geotagged satellite and perspective images from diverse urban cultures, this research characterizes personal preference in urban spaces and predicts a spectrum of unknown likeable places for a specific observer. Unlike most urban perception studies, our intention is not by any means to provide an objective measure of urban quality, but rather to portray personal views of the city or Cities of Indexes.
Tasks
Published	2020-01-23
URL	https://arxiv.org/abs/2001.10615v1
PDF	https://arxiv.org/pdf/2001.10615v1.pdf
PWC	https://paperswithcode.com/paper/indexical-cities-articulating-personal-models
Repo
Framework

A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays


Title	A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays
Authors	Chendi Rao, Jiezhang Cao, Runhao Zeng, Qi Chen, Huazhu Fu, Yanwu Xu, Mingkui Tan
Abstract	Recently, deep neural networks (DNNs) have made great progress on automated diagnosis with chest X-rays images. However, DNNs are vulnerable to adversarial examples, which may cause misdiagnoses to patients when applying the DNN based methods in disease detection. Recently, there is few comprehensive studies exploring the influence of attack and defense methods on disease detection, especially for the multi-label classification problem. In this paper, we aim to review various adversarial attack and defense methods on chest X-rays. First, the motivations and the mathematical representations of attack and defense methods are introduced in details. Second, we evaluate the influence of several state-of-the-art attack and defense methods for common thorax disease classification in chest X-rays. We found that the attack and defense methods have poor performance with excessive iterations and large perturbations. To address this, we propose a new defense method that is robust to different degrees of perturbations. This study could provide new insights into methodological development for the community.
Tasks	Adversarial Attack, Multi-Label Classification
Published	2020-03-31
URL	https://arxiv.org/abs/2003.13969v1
PDF	https://arxiv.org/pdf/2003.13969v1.pdf
PWC	https://paperswithcode.com/paper/a-thorough-comparison-study-on-adversarial
Repo
Framework

Multiple Angles of Arrival Estimation using Neural Networks


Title	Multiple Angles of Arrival Estimation using Neural Networks
Authors	Jianyuan Yu
Abstract	MUltiple SIgnal Classification (MUSIC) and Estimation of signal parameters via rotational via rotational invariance (ESPRIT) has been widely used in super resolution direction of arrival estimation (DoA) in both Uniform Linear Arrays (ULA) or Uniform Circular Arrays (UCA). However, problems become challenging when the number of source signal increase, MUSIC suffer from computation complexity when finding the peaks, while ESPRIT may not robust to array geometry offset. Therefore, Neural Network become a potential solution. In this paper, we propose a neural network to estimate the azimuth and elevation angles, based on the correlated matrix extracted from received data. Also, a serial scheme is listed to estimate multiple signals cases. The result shows the neural network can achieve an accurate estimation under low SNR and deal with multiple signals.
Tasks	Direction of Arrival Estimation, Super-Resolution
Published	2020-02-03
URL	https://arxiv.org/abs/2002.00541v1
PDF	https://arxiv.org/pdf/2002.00541v1.pdf
PWC	https://paperswithcode.com/paper/multiple-angles-of-arrival-estimation-using
Repo
Framework

CSM-NN: Current Source Model Based Logic Circuit Simulation – A Neural Network Approach


Title	CSM-NN: Current Source Model Based Logic Circuit Simulation – A Neural Network Approach
Authors	Mohammad Saeed Abrishami, Massoud Pedram, Shahin Nazarian
Abstract	The miniaturization of transistors down to 5nm and beyond, plus the increasing complexity of integrated circuits, significantly aggravate short channel effects, and demand analysis and optimization of more design corners and modes. Simulators need to model output variables related to circuit timing, power, noise, etc., which exhibit nonlinear behavior. The existing simulation and sign-off tools, based on a combination of closed-form expressions and lookup tables are either inaccurate or slow, when dealing with circuits with more than billions of transistors. In this work, we present CSM-NN, a scalable simulation framework with optimized neural network structures and processing algorithms. CSM-NN is aimed at optimizing the simulation time by accounting for the latency of the required memory query and computation, given the underlying CPU and GPU parallel processing capabilities. Experimental results show that CSM-NN reduces the simulation time by up to $6\times$ compared to a state-of-the-art current source model based simulator running on a CPU. This speedup improves by up to $15\times$ when running on a GPU. CSM-NN also provides high accuracy levels, with less than $2%$ error, compared to HSPICE.
Tasks
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05291v1
PDF	https://arxiv.org/pdf/2002.05291v1.pdf
PWC	https://paperswithcode.com/paper/csm-nn-current-source-model-based-logic
Repo
Framework

Towards a Geometry Automated Provers Competition


Title	Towards a Geometry Automated Provers Competition
Authors	Nuno Baeta, Pedro Quaresma, Zoltán Kovács
Abstract	The geometry automated theorem proving area distinguishes itself by a large number of specific methods and implementations, different approaches (synthetic, algebraic, semi-synthetic) and different goals and applications (from research in the area of artificial intelligence to applications in education). Apart from the usual measures of efficiency (e.g. CPU time), the possibility of visual and/or readable proofs is also an expected output against which the geometry automated theorem provers (GATP) should be measured. The implementation of a competition between GATP would allow to create a test bench for GATP developers to improve the existing ones and to propose new ones. It would also allow to establish a ranking for GATP that could be used by “clients” (e.g. developers of educational e-learning systems) to choose the best implementation for a given intended use.
Tasks	Automated Theorem Proving
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12556v1
PDF	https://arxiv.org/pdf/2002.12556v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-geometry-automated-provers
Repo
Framework

End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement


Title	End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement
Authors	Shurun Wang, Wenhan Yang, Shiqi Wang
Abstract	In this paper, we propose a novel end-to-end feature compression scheme by leveraging the representation and learning capability of deep neural networks, towards intelligent front-end equipped analysis with promising accuracy and efficiency. In particular, the extracted features are compactly coded in an end-to-end manner by optimizing the rate-distortion cost to achieve feature-in-feature representation. In order to further improve the compression performance, we present a latent code level teacher-student enhancement model, which could efficiently transfer the low bit-rate representation into a high bit rate one. Such a strategy further allows us to adaptively shift the representation cost to decoding computations, leading to more flexible feature compression with enhanced decoding capability. We verify the effectiveness of the proposed model with the facial feature, and experimental results reveal better compression performance in terms of rate-accuracy compared with existing models.
Tasks
Published	2020-02-10
URL	https://arxiv.org/abs/2002.03627v1
PDF	https://arxiv.org/pdf/2002.03627v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-facial-deep-learning-feature
Repo
Framework

Inline Detection of DGA Domains Using Side Information


Title	Inline Detection of DGA Domains Using Side Information
Authors	Raaghavi Sivaguru, Jonathan Peck, Femi Olumofin, Anderson Nascimento, Martine De Cock
Abstract	Malware applications typically use a command and control (C&C) server to manage bots to perform malicious activities. Domain Generation Algorithms (DGAs) are popular methods for generating pseudo-random domain names that can be used to establish a communication between an infected bot and the C&C server. In recent years, machine learning based systems have been widely used to detect DGAs. There are several well known state-of-the-art classifiers in the literature that can detect DGA domain names in real-time applications with high predictive performance. However, these DGA classifiers are highly vulnerable to adversarial attacks in which adversaries purposely craft domain names to evade DGA detection classifiers. In our work, we focus on hardening DGA classifiers against adversarial attacks. To this end, we train and evaluate state-of-the-art deep learning and random forest (RF) classifiers for DGA detection using side information that is harder for adversaries to manipulate than the domain name itself. Additionally, the side information features are selected such that they are easily obtainable in practice to perform inline DGA detection. The performance and robustness of these models is assessed by exposing them to one day of real-traffic data as well as domains generated by adversarial attack algorithms. We found that the DGA classifiers that rely on both the domain name and side information have high performance and are more robust against adversaries.
Tasks	Adversarial Attack
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05703v1
PDF	https://arxiv.org/pdf/2003.05703v1.pdf
PWC	https://paperswithcode.com/paper/inline-detection-of-dga-domains-using-side
Repo
Framework

SAD: Saliency-based Defenses Against Adversarial Examples


Title	SAD: Saliency-based Defenses Against Adversarial Examples
Authors	Richard Tran, David Patrick, Michael Geyer, Amanda Fernandez
Abstract	With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of the network and are a growing concern in practical security. In order to combat these attacks, neural networks can leverage traditional image processing approaches or state-of-the-art defensive models to reduce perturbations in the data. Defensive approaches that take a global approach to noise reduction are effective against adversarial attacks, however their lossy approach often distorts important data within the image. In this work, we propose a visual saliency based approach to cleaning data affected by an adversarial attack. Our model leverages the salient regions of an adversarial image in order to provide a targeted countermeasure while comparatively reducing loss within the cleaned images. We measure the accuracy of our model by evaluating the effectiveness of state-of-the-art saliency methods prior to attack, under attack, and after application of cleaning methods. We demonstrate the effectiveness of our proposed approach in comparison with related defenses and against established adversarial attack methods, across two saliency datasets. Our targeted approach shows significant improvements in a range of standard statistical and distance saliency metrics, in comparison with both traditional and state-of-the-art approaches.
Tasks	Adversarial Attack
Published	2020-03-10
URL	https://arxiv.org/abs/2003.04820v1
PDF	https://arxiv.org/pdf/2003.04820v1.pdf
PWC	https://paperswithcode.com/paper/sad-saliency-based-defenses-against
Repo
Framework

Agent57: Outperforming the Atari Human Benchmark


Title	Agent57: Outperforming the Atari Human Benchmark
Authors	Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Charles Blundell
Abstract	Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade. This benchmark was proposed to test general competency of RL algorithms. Previous work has achieved good average performance by doing outstandingly well on many games of the set, but very poorly in several of the most challenging games. We propose Agent57, the first deep RL agent that outperforms the standard human benchmark on all 57 Atari games. To achieve this result, we train a neural network which parameterizes a family of policies ranging from very exploratory to purely exploitative. We propose an adaptive mechanism to choose which policy to prioritize throughout the training process. Additionally, we utilize a novel parameterization of the architecture that allows for more consistent and stable learning.
Tasks	Atari Games
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13350v1
PDF	https://arxiv.org/pdf/2003.13350v1.pdf
PWC	https://paperswithcode.com/paper/agent57-outperforming-the-atari-human
Repo
Framework

Rethinking Fully Convolutional Networks for the Analysis of Photoluminescence Wafer Images


Title	Rethinking Fully Convolutional Networks for the Analysis of Photoluminescence Wafer Images
Authors	Maike Lorena Stern, Hans Lindberg, Klaus Meyer-Wegener
Abstract	The manufacturing of light-emitting diodes is a complex semiconductor-manufacturing process, interspersed with different measurements. Among the employed measurements, photoluminescence imaging has several advantages, namely being a non-destructive, fast and thus cost-effective measurement. On a photoluminescence measurement image of an LED wafer, every pixel corresponds to an LED chip’s brightness after photo-excitation, revealing chip performance information. However, generating a chip-fine defect map of the LED wafer, based on photoluminescence images, proves challenging for multiple reasons: on the one hand, the measured brightness values vary from image to image, in addition to local spots of differing brightness. On the other hand, certain defect structures may assume multiple shapes, sizes and brightness gradients, where salient brightness values may correspond to defective LED chips, measurement artefacts or non-defective structures. In this work, we revisit the creation of chip-fine defect maps using fully convolutional networks and show that the problem of segmenting objects at multiple scales can be improved by the incorporation of densely connected convolutional blocks and atrous spatial pyramid pooling modules. We also share implementation details and our experiences with training networks with small datasets of measurement images. The proposed architecture significantly improves the segmentation accuracy of highly variable defect structures over our previous version.
Tasks
Published	2020-03-01
URL	https://arxiv.org/abs/2003.00594v1
PDF	https://arxiv.org/pdf/2003.00594v1.pdf
PWC	https://paperswithcode.com/paper/rethinking-fully-convolutional-networks-for
Repo
Framework

The Sloop System for Individual Animal Identification with Deep Learning


Title	The Sloop System for Individual Animal Identification with Deep Learning
Authors	Kshitij Bakliwal, Sai Ravela
Abstract	The MIT Sloop system indexes and retrieves photographs from databases of non-stationary animal population distributions. To do this, it adaptively represents and matches generic visual feature representations using sparse relevance feedback from experts and crowds. Here, we describe the Sloop system and its application, then compare its approach to a standard deep learning formulation. We then show that priming with amplitude and deformation features requires very shallow networks to produce superior recognition results. Results suggest that relevance feedback, which enables Sloop’s high-recall performance may also be essential for deep learning approaches to individual identification to deliver comparable results.
Tasks
Published	2020-03-01
URL	https://arxiv.org/abs/2003.00559v1
PDF	https://arxiv.org/pdf/2003.00559v1.pdf
PWC	https://paperswithcode.com/paper/the-sloop-system-for-individual-animal
Repo
Framework

Regularized Adaptation for Stable and Efficient Continuous-Level Learning on Image Processing Networks


Title	Regularized Adaptation for Stable and Efficient Continuous-Level Learning on Image Processing Networks
Authors	Hyeongmin Lee, Taeoh Kim, Hanbin Son, Sangwook Baek, Minsu Cheon, Sangyoun Lee
Abstract	In Convolutional Neural Network (CNN) based image processing, most of the studies propose networks that are optimized for a single-level (or a single-objective); thus, they underperform on other levels and must be retrained for delivery of optimal performance. Using multiple models to cover multiple levels involves very high computational costs. To solve these problems, recent approaches train the networks on two different levels and propose their own interpolation methods to enable the arbitrary intermediate levels. However, many of them fail to adapt hard tasks or interpolate smoothly, or the others still require large memory and computational cost. In this paper, we propose a novel continuous-level learning framework using a Filter Transition Network (FTN) which is a non-linear module that easily adapt to new levels, and is regularized to prevent undesirable side-effects. Additionally, for stable learning of FTN, we newly propose a method to initialize non-linear CNNs with identity mappings. Furthermore, FTN is extremely lightweight module since it is a data-independent module, which means it is not affected by the spatial resolution of the inputs. Extensive results for various image processing tasks indicate that the performance of FTN is stable in terms of adaptation and interpolation, and comparable to that of the other heavy frameworks.
Tasks
Published	2020-03-11
URL	https://arxiv.org/abs/2003.05145v2
PDF	https://arxiv.org/pdf/2003.05145v2.pdf
PWC	https://paperswithcode.com/paper/regularized-adaptation-for-stable-and
Repo
Framework