January 27, 2020

3284 words 16 mins read

Paper Group ANR 1295

Computational Flight Control: A Domain-Knowledge-Aided Deep Reinforcement Learning Approach. Identity Document and banknote security forensics: a survey. Collective Learning. Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP. Spatially Constrained Generative Adversarial Networks for Conditional Image Generation. …

Computational Flight Control: A Domain-Knowledge-Aided Deep Reinforcement Learning Approach


Title	Computational Flight Control: A Domain-Knowledge-Aided Deep Reinforcement Learning Approach
Authors	Hyo-Sang Shin, Shaoming He, Antonios Tsourdos
Abstract	This papers aims to examine the potential of using the emerging deep reinforcement learning techniques in flight control. Instead of learning from scratch, the autopilot structure is fixed as typical three-loop autopilot and deep reinforcement learning is utilised to learn the autopilot gains. This domain-knowledge-aided approach is proved to significantly improve the learning efficiency. To solve the flight control problem, we then formulate a Markovian decision process with a proper reward function that enable the application of reinforcement learning theory. The state-of-the-art deep deterministic policy gradient algorithm is utilised to learn an action policy that maps the observed states to the autopilot gains. Extensive empirical numerical simulations are performed to validate the proposed computational control algorithm.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06884v1
PDF	https://arxiv.org/pdf/1908.06884v1.pdf
PWC	https://paperswithcode.com/paper/computational-flight-control-a-domain
Repo
Framework

Identity Document and banknote security forensics: a survey


Title	Identity Document and banknote security forensics: a survey
Authors	Albert Berenguel Centeno, Oriol Ramos Terrades, Josep Lladós Canet, Cristina Cañero Morales
Abstract	Counterfeiting and piracy are a form of theft that has been steadily growing in recent years. Banknotes and identity documents are two common objects of counterfeiting. Aiming to detect these counterfeits, the present survey covers a wide range of anti-counterfeiting security features, categorizing them into three components: security substrate, security inks and security printing. respectively. From the computer vision perspective, we present works in the literature covering these three categories. Other topics, such as history of counterfeiting, effects on society and document experts, counterfeiter types of attacks, trends among others are covered. Therefore, from non-experienced to professionals in security documents, can be introduced or deepen its knowledge in anti-counterfeiting measures.
Tasks
Published	2019-10-20
URL	https://arxiv.org/abs/1910.08993v1
PDF	https://arxiv.org/pdf/1910.08993v1.pdf
PWC	https://paperswithcode.com/paper/identity-document-and-banknote-security
Repo
Framework

Collective Learning


Title	Collective Learning
Authors	Francesco Farina
Abstract	In this paper, we introduce the concept of collective learning (CL) which exploits the notion of collective intelligence in the field of distributed semi-supervised learning. The proposed framework draws inspiration from the learning behavior of human beings, who alternate phases involving collaboration, confrontation and exchange of views with other consisting of studying and learning on their own. On this regard, CL comprises two main phases: a self-training phase in which learning is performed on local private (labeled) data only and a collective training phase in which proxy-labels are assigned to shared (unlabeled) data by means of a consensus-based algorithm. In the considered framework, heterogeneous systems can be connected over the same network, each with different computational capabilities and resources and everyone in the network may take advantage of the cooperation and will eventually reach higher performance with respect to those it can reach on its own. An extensive experimental campaign on an image classification problem emphasizes the properties of CL by analyzing the performance achieved by the cooperating agents.
Tasks	Image Classification
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02580v1
PDF	https://arxiv.org/pdf/1912.02580v1.pdf
PWC	https://paperswithcode.com/paper/collective-learning
Repo
Framework

Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP


Title	Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP
Authors	Haonan Yu, Sergey Edunov, Yuandong Tian, Ari S. Morcos
Abstract	The lottery ticket hypothesis proposes that over-parameterization of deep neural networks (DNNs) aids training by increasing the probability of a “lucky” sub-network initialization being present rather than by helping the optimization process (Frankle & Carbin, 2019). Intriguingly, this phenomenon suggests that initialization strategies for DNNs can be improved substantially, but the lottery ticket hypothesis has only previously been tested in the context of supervised learning for natural image tasks. Here, we evaluate whether “winning ticket” initializations exist in two different domains: natural language processing (NLP) and reinforcement learning (RL).For NLP, we examined both recurrent LSTM models and large-scale Transformer models (Vaswani et al., 2017). For RL, we analyzed a number of discrete-action space tasks, including both classic control and pixel control. Consistent with workin supervised image classification, we confirm that winning ticket initializations generally outperform parameter-matched random initializations, even at extreme pruning rates for both NLP and RL. Notably, we are able to find winning ticket initializations for Transformers which enable models one-third the size to achieve nearly equivalent performance. Together, these results suggest that the lottery ticket hypothesis is not restricted to supervised learning of natural images, but rather represents a broader phenomenon in DNNs.
Tasks	Image Classification
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02768v3
PDF	https://arxiv.org/pdf/1906.02768v3.pdf
PWC	https://paperswithcode.com/paper/playing-the-lottery-with-rewards-and-multiple
Repo
Framework

Spatially Constrained Generative Adversarial Networks for Conditional Image Generation


Title	Spatially Constrained Generative Adversarial Networks for Conditional Image Generation
Authors	Songyao Jiang, Hongfu Liu, Yue Wu, Yun Fu
Abstract	Image generation has raised tremendous attention in both academic and industrial areas, especially for the conditional and target-oriented image generation, such as criminal portrait and fashion design. Although the current studies have achieved preliminary results along this direction, they always focus on class labels as the condition where spatial contents are randomly generated from latent vectors. Edge details are usually blurred since spatial information is difficult to preserve. In light of this, we propose a novel Spatially Constrained Generative Adversarial Network (SCGAN), which decouples the spatial constraints from the latent vector and makes these constraints feasible as additional controllable signals. To enhance the spatial controllability, a generator network is specially designed to take a semantic segmentation, a latent vector and an attribute-level label as inputs step by step. Besides, a segmentor network is constructed to impose spatial constraints on the generator. Experimentally, we provide both visual and quantitative results on CelebA and DeepFashion datasets, and demonstrate that the proposed SCGAN is very effective in controlling the spatial contents as well as generating high-quality images.
Tasks	Conditional Image Generation, Image Generation, Semantic Segmentation
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02320v1
PDF	https://arxiv.org/pdf/1905.02320v1.pdf
PWC	https://paperswithcode.com/paper/spatially-constrained-generative-adversarial
Repo
Framework

Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation


Title	Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation
Authors	Marco Ancona, Cengiz Öztireli, Markus Gross
Abstract	The problem of explaining the behavior of deep neural networks has recently gained a lot of attention. While several attribution methods have been proposed, most come without strong theoretical foundations, which raises questions about their reliability. On the other hand, the literature on cooperative game theory suggests Shapley values as a unique way of assigning relevance scores such that certain desirable properties are satisfied. Unfortunately, the exact evaluation of Shapley values is prohibitively expensive, exponential in the number of input features. In this work, by leveraging recent results on uncertainty propagation, we propose a novel, polynomial-time approximation of Shapley values in deep neural networks. We show that our method produces significantly better approximations of Shapley values than existing state-of-the-art attribution methods.
Tasks
Published	2019-03-26
URL	https://arxiv.org/abs/1903.10992v4
PDF	https://arxiv.org/pdf/1903.10992v4.pdf
PWC	https://paperswithcode.com/paper/explaining-deep-neural-networks-with-a
Repo
Framework

Cross-Layer Strategic Ensemble Defense Against Adversarial Examples


Title	Cross-Layer Strategic Ensemble Defense Against Adversarial Examples
Authors	Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow, Emre Gursoy, Stacey Truex, Yanzhao Wu
Abstract	Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble framework and a suite of robust defense algorithms, which are attack-independent, and capable of auto-repairing and auto-verifying the target model being attacked. Our strategic ensemble approach makes three original contributions. First, we employ input-transformation diversity to design the input-layer strategic transformation ensemble algorithms. Second, we utilize model-disagreement diversity to develop the output-layer strategic model ensemble algorithms. Finally, we create an input-output cross-layer strategic ensemble defense that strengthens the defensibility by combining diverse input transformation based model ensembles with diverse output verification model ensembles. Evaluated over 10 attacks on ImageNet dataset, we show that our strategic ensemble defense algorithms can achieve high defense success rates and are more robust with high attack prevention success rates and low benign false negative rates, compared to existing representative defense methods.
Tasks
Published	2019-10-01
URL	https://arxiv.org/abs/1910.01742v1
PDF	https://arxiv.org/pdf/1910.01742v1.pdf
PWC	https://paperswithcode.com/paper/cross-layer-strategic-ensemble-defense
Repo
Framework

Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction


Title	Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
Authors	Lingbo Liu, Zhilin Qiu, Guanbin Li, Qing Wang, Wanli Ouyang, Liang Lin
Abstract	Taxi demand prediction has recently attracted increasing research interest due to its huge potential application in large-scale intelligent transportation systems. However, most of the previous methods only considered the taxi demand prediction in origin regions, but neglected the modeling of the specific situation of the destination passengers. We believe it is suboptimal to preallocate the taxi into each region based solely on the taxi origin demand. In this paper, we present a challenging and worth-exploring task, called taxi origin-destination demand prediction, which aims at predicting the taxi demand between all region pairs in a future time interval. Its main challenges come from how to effectively capture the diverse contextual information to learn the demand patterns. We address this problem with a novel Contextualized Spatial-Temporal Network (CSTN), which consists of three components for the modeling of local spatial context (LSC), temporal evolution context (TEC) and global correlation context (GCC) respectively. Firstly, an LSC module utilizes two convolution neural networks to learn the local spatial dependencies of taxi demand respectively from the origin view and the destination view. Secondly, a TEC module incorporates both the local spatial features of taxi demand and the meteorological information to a Convolutional Long Short-term Memory Network (ConvLSTM) for the analysis of taxi demand evolution. Finally, a GCC module is applied to model the correlation between all regions by computing a global correlation feature as a weighted sum of all regional features, with the weights being calculated as the similarity between the corresponding region pairs. Extensive experiments and evaluations on a large-scale dataset well demonstrate the superiority of our CSTN over other compared methods for taxi origin-destination demand prediction.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06335v1
PDF	https://arxiv.org/pdf/1905.06335v1.pdf
PWC	https://paperswithcode.com/paper/contextualized-spatial-temporal-network-for
Repo
Framework

Gradient Boosting to Boost the Efficiency of Hydraulic Fracturing


Title	Gradient Boosting to Boost the Efficiency of Hydraulic Fracturing
Authors	Ivan Makhotin, Dmitry Koroteev, Evgeny Burnaev
Abstract	In this paper, we present a data-driven model for forecasting the production increase after hydraulic fracturing (HF). We use data from fracturing jobs performed at one of the Siberian oilfields. The data includes features, characterizing the jobs, and geological information. To predict an oil rate after the fracturing machine learning (ML) technique was applied. We compared the ML-based prediction to a prediction based on the experience of reservoir and production engineers responsible for the HF-job planning. We discuss the potential for further development of ML techniques for predicting changes in oil rate after HF.
Tasks
Published	2019-02-05
URL	https://arxiv.org/abs/1902.02223v3
PDF	https://arxiv.org/pdf/1902.02223v3.pdf
PWC	https://paperswithcode.com/paper/gradient-boosting-to-boost-the-efficiency-of
Repo
Framework

Deep learning enabled multi-wavelength spatial coherence microscope for the classification of malaria-infected stages with limited labelled data size


Title	Deep learning enabled multi-wavelength spatial coherence microscope for the classification of malaria-infected stages with limited labelled data size
Authors	Neeru Singla, Vishal Srivastava
Abstract	Malaria is a life-threatening mosquito-borne blood disease, hence early detection is very crucial for health. The conventional method for the detection is a microscopic examination of Giemsa-stained blood smears, which needs a highly trained skilled technician. Automated classifications of different stages of malaria still a challenging task, especially having poor sensitivity in detecting the early trophozoite and late trophozoite or schizont stage with limited labelled datasize. The study aims to develop a fast, robust and fully automated system for the classification of different stages of malaria with limited data size by using the pre-trained convolutional neural networks (CNNs) as a classifier and multi-wavelength to increase the sample size. We also compare our customized CNN with other well-known CNNs and shows that our network have a comparable performance with less computational time. We believe that our proposed method can be applied to other limited labelled biological datasets.
Tasks
Published	2019-03-14
URL	http://arxiv.org/abs/1903.06056v1
PDF	http://arxiv.org/pdf/1903.06056v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-enabled-multi-wavelength
Repo
Framework

Comparing Sample-wise Learnability Across Deep Neural Network Models


Title	Comparing Sample-wise Learnability Across Deep Neural Network Models
Authors	Seung-Geon Lee, Jaedeok Kim, Hyun-Joo Jung, Yoonsuck Choe
Abstract	Estimating the relative importance of each sample in a training set has important practical and theoretical value, such as in importance sampling or curriculum learning. This kind of focus on individual samples invokes the concept of sample-wise learnability: How easy is it to correctly learn each sample (cf. PAC learnability)? In this paper, we approach the sample-wise learnability problem within a deep learning context. We propose a measure of the learnability of a sample with a given deep neural network (DNN) model. The basic idea is to train the given model on the training set, and for each sample, aggregate the hits and misses over the entire training epochs. Our experiments show that the sample-wise learnability measure collected this way is highly linearly correlated across different DNN models (ResNet-20, VGG-16, and MobileNet), suggesting that such a measure can provide deep general insights on the data’s properties. We expect our method to help develop better curricula for training, and help us better understand the data itself.
Tasks
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02347v1
PDF	http://arxiv.org/pdf/1901.02347v1.pdf
PWC	https://paperswithcode.com/paper/comparing-sample-wise-learnability-across
Repo
Framework

Skeleton based Activity Recognition by Fusing Part-wise Spatio-temporal and Attention Driven Residues


Title	Skeleton based Activity Recognition by Fusing Part-wise Spatio-temporal and Attention Driven Residues
Authors	Chhavi Dhiman, Dinesh Kumar Vishwakarma, Paras Aggarwal
Abstract	There exist a wide range of intra class variations of the same actions and inter class similarity among the actions, at the same time, which makes the action recognition in videos very challenging. In this paper, we present a novel skeleton-based part-wise Spatiotemporal CNN RIAC Network-based 3D human action recognition framework to visualise the action dynamics in part wise manner and utilise each part for action recognition by applying weighted late fusion mechanism. Part wise skeleton based motion dynamics helps to highlight local features of the skeleton which is performed by partitioning the complete skeleton in five parts such as Head to Spine, Left Leg, Right Leg, Left Hand, Right Hand. The RIAFNet architecture is greatly inspired by the InceptionV4 architecture which unified the ResNet and Inception based Spatio-temporal feature representation concept and achieving the highest top-1 accuracy till date. To extract and learn salient features for action recognition, attention driven residues are used which enhance the performance of residual components for effective 3D skeleton-based Spatio-temporal action representation. The robustness of the proposed framework is evaluated by performing extensive experiments on three challenging datasets such as UT Kinect Action 3D, Florence 3D action Dataset, and MSR Daily Action3D datasets, which consistently demonstrate the superiority of our method
Tasks	3D Human Action Recognition, Action Recognition In Videos, Activity Recognition, Temporal Action Localization
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00576v1
PDF	https://arxiv.org/pdf/1912.00576v1.pdf
PWC	https://paperswithcode.com/paper/skeleton-based-activity-recognition-by-fusing
Repo
Framework

AEGR: A simple approach to gradient reversal in autoencoders for network anomaly detection


Title	AEGR: A simple approach to gradient reversal in autoencoders for network anomaly detection
Authors	Kasra Babaei, Zhi Yuan Chen, Tomas Maul
Abstract	Anomaly detection is referred to as a process in which the aim is to detect data points that follow a different pattern from the majority of data points. Anomaly detection methods suffer from several well-known challenges that hinder their performance such as high dimensionality. Autoencoders are unsupervised neural networks that have been used for the purpose of reducing dimensionality and also detecting network anomalies in large datasets. The performance of autoencoders debilitates when the training set contains noise and anomalies. In this paper, a new gradient-reversal method is proposed to overcome the influence of anomalies on the training phase for the purpose of detecting network anomalies. The method is different from other approaches as it does not require an anomaly-free training set and is based on reconstruction error. Once latent variables are extracted from the network, Local Outlier Factor is used to separate normal data points from anomalies. A simple pruning approach and data augmentation is also added to further improve performance. The experimental results show that the proposed model can outperform other well-know approaches.
Tasks	Anomaly Detection, Data Augmentation
Published	2019-12-21
URL	https://arxiv.org/abs/1912.13387v2
PDF	https://arxiv.org/pdf/1912.13387v2.pdf
PWC	https://paperswithcode.com/paper/aegr-a-simple-approach-to-gradient-reversal
Repo
Framework

Good Similar Patches for Image Denoising


Title	Good Similar Patches for Image Denoising
Authors	Si Lu
Abstract	Patch-based denoising algorithms like BM3D have achieved outstanding performance. An important idea for the success of these methods is to exploit the recurrence of similar patches in an input image to estimate the underlying image structures. However, in these algorithms, the similar patches used for denoising are obtained via Nearest Neighbour Search (NNS) and are sometimes not optimal. First, due to the existence of noise, NNS can select similar patches with similar noise patterns to the reference patch. Second, the unreliable noisy pixels in digital images can bring a bias to the patch searching process and result in a loss of color fidelity in the final denoising result. We observe that given a set of good similar patches, their distribution is not necessarily centered at the noisy reference patch and can be approximated by a Gaussian component. Based on this observation, we present a patch searching method that clusters similar patch candidates into patch groups using Gaussian Mixture Model-based clustering, and selects the patch group that contains the reference patch as the final patches for denoising. We also use an unreliable pixel estimation algorithm to pre-process the input noisy images to further improve the patch searching. Our experiments show that our approach can better capture the underlying patch structures and can consistently enable the state-of-the-art patch-based denoising algorithms, such as BM3D, LPCA and PLOW, to better denoise images by providing them with patches found by our approach while without modifying these algorithms.
Tasks	Denoising, Image Denoising
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06046v1
PDF	http://arxiv.org/pdf/1901.06046v1.pdf
PWC	https://paperswithcode.com/paper/good-similar-patches-for-image-denoising
Repo
Framework

A Robot for Nondestructive Assay of Holdup Deposits in Gaseous Diffusion Piping


Title	A Robot for Nondestructive Assay of Holdup Deposits in Gaseous Diffusion Piping
Authors	Heather Jones, Siri Maley, Mohammadreza Mousaei, David Kohanbash, Warren Whittaker, James Teza, Andrew Zhang, Nikhil Jog, William Whittaker
Abstract	Miles of contaminated pipe must be measured, foot by foot, as part of the decommissioning effort at deactivated gaseous diffusion enrichment facilities. The current method requires cutting away asbestos-lined thermal enclosures and performing repeated, elevated operations to manually measure pipe from the outside. The RadPiper robot, part of the Pipe Crawling Activity Measurement System (PCAMS) developed by Carnegie Mellon University and commissioned for use at the DOE Portsmouth Gaseous Diffusion Enrichment Facility, automatically measures U-235 in pipes from the inside. This improves certainty, increases safety, and greatly reduces measurement time. The heart of the RadPiper robot is a sodium iodide scintillation detector in an innovative disc-collimated assembly. By measuring from inside pipes, the robot significantly increases its count rate relative to external through-pipe measurements. The robot also provides imagery, models interior pipe geometry, and precisely measures distance in order to localize radiation measurements. Data collected by this system provides insight into pipe interiors that is simply not possible from exterior measurements, all while keeping operators safer. This paper describes the technical details of the PCAMS RadPiper robot. Key features for this robot include precision distance measurement, in-pipe obstacle detection, ability to transform for two pipe sizes, and robustness in autonomous operation. Test results demonstrating the robot’s functionality are presented, including deployment tolerance tests, safeguarding tests, and localization tests. Integrated robot tests are also shown.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10341v1
PDF	http://arxiv.org/pdf/1901.10341v1.pdf
PWC	https://paperswithcode.com/paper/a-robot-for-nondestructive-assay-of-holdup
Repo
Framework