January 27, 2020

3268 words 16 mins read

Paper Group ANR 1322

Face Detection in Camera Captured Images of Identity Documents under Challenging Conditions. Self-Selective Correlation Ship Tracking Method for Smart Ocean System. Rethinking Arithmetic for Deep Neural Networks. Textual analysis of artificial intelligence manuscripts reveals features associated with peer review outcome. Longitudinal Motion Plannin …

Face Detection in Camera Captured Images of Identity Documents under Challenging Conditions


Title	Face Detection in Camera Captured Images of Identity Documents under Challenging Conditions
Authors	Souhail Bakkali, Zuheng Ming, Muhammad Muzzamil Luqman, Jean-Christophe Burie
Abstract	Benefiting from the advance of deep convolutional neural network approaches (CNNs), many face detection algorithms have achieved state-of-the-art performance in terms of accuracy and very high speed in unconstrained applications. However, due to the lack of public datasets and due to the variation of the orientation of face images, the complex background and lighting, defocus and the varying illumination of camera captured images, face detection on identity documents under unconstrained environments has not been sufficiently studied. To address this problem more efficiently, we survey three state-of-the-art face detection methods based on general images, i.e. Cascade-CNN, MTCNN and PCN, for face detection in camera captured images of identity documents, given different image quality assessments. For that, The MIDV-500 dataset, which is the largest and most challenging dataset for identity documents, is used to evaluate the three methods. The evaluation results show the performance and the limitations of the current methods for face detection on identity documents under the wild complex environments. These results show that the face detection task in camera captured images of identity documents is challenging, providing a space to improve in the future works.
Tasks	Face Detection
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03567v1
PDF	https://arxiv.org/pdf/1911.03567v1.pdf
PWC	https://paperswithcode.com/paper/face-detection-in-camera-captured-images-of
Repo
Framework

Self-Selective Correlation Ship Tracking Method for Smart Ocean System


Title	Self-Selective Correlation Ship Tracking Method for Smart Ocean System
Authors	Xu Kang, Bin Song, Jie Guo, Xiaojiang Du, Mohsen Guizani
Abstract	In recent years, with the development of the marine industry, navigation environment becomes more complicated. Some artificial intelligence technologies, such as computer vision, can recognize, track and count the sailing ships to ensure the maritime security and facilitates the management for Smart Ocean System. Aiming at the scaling problem and boundary effect problem of traditional correlation filtering methods, we propose a self-selective correlation filtering method based on box regression (BRCF). The proposed method mainly include: 1) A self-selective model with negative samples mining method which effectively reduces the boundary effect in strengthening the classification ability of classifier at the same time; 2) A bounding box regression method combined with a key points matching method for the scale prediction, leading to a fast and efficient calculation. The experimental results show that the proposed method can effectively deal with the problem of ship size changes and background interference. The success rates and precisions were higher than Discriminative Scale Space Tracking (DSST) by over 8 percentage points on the marine traffic dataset of our laboratory. In terms of processing speed, the proposed method is higher than DSST by nearly 22 Frames Per Second (FPS).
Tasks
Published	2019-02-26
URL	http://arxiv.org/abs/1902.09690v1
PDF	http://arxiv.org/pdf/1902.09690v1.pdf
PWC	https://paperswithcode.com/paper/self-selective-correlation-ship-tracking
Repo
Framework

Rethinking Arithmetic for Deep Neural Networks


Title	Rethinking Arithmetic for Deep Neural Networks
Authors	George A. Constantinides
Abstract	We consider efficiency in the implementation of deep neural networks. Hardware accelerators are gaining interest as machine learning becomes one of the drivers of high-performance computing. In these accelerators, the directed graph describing a neural network can be implemented as a directed graph describing a Boolean circuit. We make this observation precise, leading naturally to an understanding of practical neural networks as discrete functions, and show that so-called binarised neural networks are functionally complete. In general, our results suggest that it is valuable to consider Boolean circuits as neural networks, leading to the question of which circuit topologies are promising. We argue that continuity is central to generalisation in learning, explore the interaction between data coding, network topology, and node functionality for continuity, and pose some open questions for future research. As a first step to bridging the gap between continuous and Boolean views of neural network accelerators, we present some recent results from our work on LUTNet, a novel Field-Programmable Gate Array inference approach. Finally, we conclude with additional possible fruitful avenues for research bridging the continuous and discrete views of neural networks.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02438v2
PDF	https://arxiv.org/pdf/1905.02438v2.pdf
PWC	https://paperswithcode.com/paper/rethinking-arithmetic-for-deep-neural
Repo
Framework

Textual analysis of artificial intelligence manuscripts reveals features associated with peer review outcome


Title	Textual analysis of artificial intelligence manuscripts reveals features associated with peer review outcome
Authors	Philippe Vincent-Lamarre, Vincent Larivière
Abstract	We analysed a dataset of scientific manuscripts that were submitted to various conferences in artificial intelligence. We performed a combination of semantic, lexical and psycholinguistic analyses of the full text of the manuscripts and compared them with the outcome of the peer review process. We found that accepted manuscripts scored lower than rejected manuscripts on two indicators of readability, and that they also used more scientific and artificial intelligence jargon. We also found that accepted manuscripts were written with words that are less frequent, that are acquired at an older age, and that are more abstract than rejected manuscripts. The analysis of references included in the manuscripts revealed that the subset of accepted submissions were more likely to cite the same publications. This finding was echoed by pairwise comparisons of the word content of the manuscripts (i.e. an indicator or semantic similarity), which were more similar in the subset of accepted manuscripts. Finally, we predicted the peer review outcome of manuscripts with their word content, with words related to machine learning and neural networks positively related with acceptance, whereas words related to logic, symbolic processing and knowledge-based systems negatively related with acceptance.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2019-10-21
URL	https://arxiv.org/abs/1911.02648v2
PDF	https://arxiv.org/pdf/1911.02648v2.pdf
PWC	https://paperswithcode.com/paper/content-and-linguistic-biases-in-the-peer
Repo
Framework

Longitudinal Motion Planning for Autonomous Vehicles and Its Impact on Congestion: A Survey


Title	Longitudinal Motion Planning for Autonomous Vehicles and Its Impact on Congestion: A Survey
Authors	Hao Zhou, Jorge Laval
Abstract	This paper reviews machine learning methods for the motion planning of autonomous vehicles (AVs), with exclusive focus on the longitudinal behaviors and their impact on traffic congestion. An extensive survey of training data, model input/output, and learning methods for machine learning longitudinal motion planning (mMP) is first presented. Each of those major components is discussed and evaluated from the perspective of congestion impact. The emerging technologies adopted by leading AV giants like Waymo and Tesla are highlighted in our review. We find that: i) the AV industry has been focusing on the long tail problem caused by “corner errors” threatening driving safety, ii) none of the existing public datasets provides sufficient data under congestion scenarios, and iii) although alternative and more advanced learning methods are available in literature, the major mMP method adopted by industry is still behavior cloning (BC). The study also surveys the connections between mMP and traditional car-following (CF) models, and it reveals that: i) the model equivalence only exists in simple settings, ii) studies have shown mMP can significantly outperform CF models in long-term speed prediction, and iii) mMP’s string stability remains intractable yet, which can only be analyzed by model approximation followed with numerical simulations. Future research needs are also identified in the end.
Tasks	Autonomous Vehicles, Motion Planning
Published	2019-10-02
URL	https://arxiv.org/abs/1910.06070v1
PDF	https://arxiv.org/pdf/1910.06070v1.pdf
PWC	https://paperswithcode.com/paper/longitudinal-motion-planning-for-autonomous
Repo
Framework

From semantics to execution: Integrating action planning with reinforcement learning for robotic causal problem-solving


Title	From semantics to execution: Integrating action planning with reinforcement learning for robotic causal problem-solving
Authors	Manfred Eppe, Phuong D. H. Nguyen, Stefan Wermter
Abstract	Reinforcement learning is an appropriate and successful method to robustly perform low-level robot control under noisy conditions. Symbolic action planning is useful to resolve causal dependencies and to break a causally complex problem down into a sequence of simpler high-level actions. A problem with the integration of both approaches is that action planning is based on discrete high-level action- and state spaces, whereas reinforcement learning is usually driven by a continuous reward function. However, recent advances in reinforcement learning, specifically, universal value function approximators and hindsight experience replay, have focused on goal-independent methods based on sparse rewards. In this article, we build on these novel methods to facilitate the integration of action planning with reinforcement learning by exploiting the reward-sparsity as a bridge between the high-level and low-level state- and control spaces. As a result, we demonstrate that the integrated neuro-symbolic method is able to solve object manipulation problems that involve tool use and non-trivial causal dependencies under noisy conditions, exploiting both data and knowledge.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09683v2
PDF	https://arxiv.org/pdf/1905.09683v2.pdf
PWC	https://paperswithcode.com/paper/from-semantics-to-execution-integrating
Repo
Framework

Robust Metric Learning based on the Rescaled Hinge Loss


Title	Robust Metric Learning based on the Rescaled Hinge Loss
Authors	Sumia Abdulhussien Razooqi Al-Obaidi, Davood Zabihzadeh, Hamideh Hajiabadi
Abstract	Distance/Similarity learning is a fundamental problem in machine learning. For example, kNN classifier or clustering methods are based on a distance/similarity measure. Metric learning algorithms enhance the efficiency of these methods by learning an optimal distance function from data. Most metric learning methods need training information in the form of pair or triplet sets. Nowadays, this training information often is obtained from the Internet via crowdsourcing methods. Therefore, this information may contain label noise or outliers leading to the poor performance of the learned metric. It is even possible that the learned metric functions perform worse than the general metrics such as Euclidean distance. To address this challenge, this paper presents a new robust metric learning method based on the Rescaled Hinge loss. This loss function is a general case of the popular Hinge loss and initially introduced in (Xu et al. 2017) to develop a new robust SVM algorithm. In this paper, we formulate the metric learning problem using the Rescaled Hinge loss function and then develop an efficient algorithm based on HQ (Half-Quadratic) to solve the problem. Experimental results on a variety of both real and synthetic datasets confirm that our new robust algorithm considerably outperforms state-of-the-art metric learning methods in the presence of label noise and outliers.
Tasks	Metric Learning
Published	2019-04-26
URL	https://arxiv.org/abs/1904.11711v2
PDF	https://arxiv.org/pdf/1904.11711v2.pdf
PWC	https://paperswithcode.com/paper/robust-metric-learning-based-on-the-rescaled
Repo
Framework

Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation


Title	Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation
Authors	Arijit Ray, Karan Sikka, Ajay Divakaran, Stefan Lee, Giedrius Burachas
Abstract	While models for Visual Question Answering (VQA) have steadily improved over the years, interacting with one quickly reveals that these models lack consistency. For instance, if a model answers “red” to “What color is the balloon?", it might answer “no” if asked, “Is the balloon red?". These responses violate simple notions of entailment and raise questions about how effectively VQA models ground language. In this work, we introduce a dataset, ConVQA, and metrics that enable quantitative evaluation of consistency in VQA. For a given observable fact in an image (e.g. the balloon’s color), we generate a set of logically consistent question-answer (QA) pairs (e.g. Is the balloon red?) and also collect a human-annotated set of common-sense based consistent QA pairs (e.g. Is the balloon the same color as tomato sauce?). Further, we propose a consistency-improving data augmentation module, a Consistency Teacher Module (CTM). CTM automatically generates entailed (or similar-intent) questions for a source QA pair and fine-tunes the VQA model if the VQA’s answer to the entailed question is consistent with the source QA pair. We demonstrate that our CTM-based training improves the consistency of VQA models on the ConVQA datasets and is a strong baseline for further research.
Tasks	Common Sense Reasoning, Data Augmentation, Question Answering, Question Generation, Visual Question Answering
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04696v1
PDF	https://arxiv.org/pdf/1909.04696v1.pdf
PWC	https://paperswithcode.com/paper/sunny-and-dark-outside-improving-answer
Repo
Framework

Reconstruction of 3D Porous Media From 2D Slices


Title	Reconstruction of 3D Porous Media From 2D Slices
Authors	Denis Volkhonskiy, Ekaterina Muravleva, Oleg Sudakov, Denis Orlov, Boris Belozerov, Evgeny Burnaev, Dmitry Koroteev
Abstract	In many branches of earth sciences, the problem of rock study on the micro-level arises. However, a significant number of representative samples is not always feasible. Thus the problem of the generation of samples with similar properties becomes actual. In this paper, we propose a novel deep learning architecture for three-dimensional porous media reconstruction from two-dimensional slices. We fit a distribution on all possible three-dimensional structures of a specific type based on the given dataset of samples. Then, given partial information (central slices) we recover the three-dimensional structure around such slices as the most probable one according to that constructed distribution. Technically, we implement this in the form of a deep neural network with encoder, generator and discriminator modules. Numerical experiments show that this method provides good reconstruction in terms of Minkowski functionals.
Tasks
Published	2019-01-29
URL	https://arxiv.org/abs/1901.10233v3
PDF	https://arxiv.org/pdf/1901.10233v3.pdf
PWC	https://paperswithcode.com/paper/reconstruction-of-3d-porous-media-from-2d
Repo
Framework

Improved BiGAN training with marginal likelihood equalization


Title	Improved BiGAN training with marginal likelihood equalization
Authors	Pablo Sánchez-Martín, Pablo M. Olmos, Fernando Perez-Cruz
Abstract	We propose a novel training procedure for improving the performance of generative adversarial networks (GANs), especially to bidirectional GANs. First, we enforce that the empirical distribution of the inverse inference network matches the prior distribution, which favors the generator network reproducibility on the seen samples. Second, we have found that the marginal log-likelihood of the samples shows a severe overrepresentation of a certain type of samples. To address this issue, we propose to train the bidirectional GAN using a non-uniform sampling for the mini-batch selection, resulting in improved quality and variety in generated samples measured quantitatively and by visual inspection. We illustrate our new procedure with the well-known CIFAR10, Fashion MNIST and CelebA datasets.
Tasks
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01425v1
PDF	https://arxiv.org/pdf/1911.01425v1.pdf
PWC	https://paperswithcode.com/paper/improved-bigan-training-with-marginal
Repo
Framework

Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night


Title	Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night
Authors	Wenyan Cong, Jianfu Zhang, Li Niu, Liu Liu, Zhixin Ling, Weiyuan Li, Liqing Zhang
Abstract	Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image. Image harmonization, which aims to make the foreground compatible with the background, is a promising yet challenging task. However, the lack of high-quality public dataset for image harmonization, which significantly hinders the development of image harmonization techniques. Therefore, we contribute an image harmonization dataset iHarmony4 by generating synthesized composite images based on existing COCO (resp., Adobe5k, day2night) dataset, leading to our HCOCO (resp., HAdobe5k, Hday2night) sub-dataset. To enrich the diversity of our dataset, we also generate synthesized composite images based on our collected Flick images, leading to our HFlickr sub-dataset. The image harmonization dataset iHarmony4 is released at https://github.com/bcmi/Image_Harmonization_Datasets.
Tasks
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10526v4
PDF	https://arxiv.org/pdf/1908.10526v4.pdf
PWC	https://paperswithcode.com/paper/image-harmonization-datasets-hcoco-hadobe5k
Repo
Framework

Survey of Attacks and Defenses on Edge-Deployed Neural Networks


Title	Survey of Attacks and Defenses on Edge-Deployed Neural Networks
Authors	Mihailo Isakov, Vijay Gadepally, Karen M. Gettings, Michel A. Kinsy
Abstract	Deep Neural Network (DNN) workloads are quickly moving from datacenters onto edge devices, for latency, privacy, or energy reasons. While datacenter networks can be protected using conventional cybersecurity measures, edge neural networks bring a host of new security challenges. Unlike classic IoT applications, edge neural networks are typically very compute and memory intensive, their execution is data-independent, and they are robust to noise and faults. Neural network models may be very expensive to develop, and can potentially reveal information about the private data they were trained on, requiring special care in distribution. The hidden states and outputs of the network can also be used in reconstructing user inputs, potentially violating users’ privacy. Furthermore, neural networks are vulnerable to adversarial attacks, which may cause misclassifications and violate the integrity of the output. These properties add challenges when securing edge-deployed DNNs, requiring new considerations, threat models, priorities, and approaches in securely and privately deploying DNNs to the edge. In this work, we cover the landscape of attacks on, and defenses, of neural networks deployed in edge devices and provide a taxonomy of attacks and defenses targeting edge DNNs.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.11932v1
PDF	https://arxiv.org/pdf/1911.11932v1.pdf
PWC	https://paperswithcode.com/paper/survey-of-attacks-and-defenses-on-edge
Repo
Framework

An Efficient Machine Learning-based Elderly Fall Detection Algorithm


Title	An Efficient Machine Learning-based Elderly Fall Detection Algorithm
Authors	Faisal Hussain, Muhammad Basit Umair, Muhammad Ehatisham-ul-Haq, Ivan Miguel Pires, Tânia Valente, Nuno M. Garcia, Nuno Pombo
Abstract	Falling is a commonly occurring mishap with elderly people, which may cause serious injuries. Thus, rapid fall detection is very important in order to mitigate the severe effects of fall among the elderly people. Many fall monitoring systems based on the accelerometer have been proposed for the fall detection. However, many of them mistakenly identify the daily life activities as fall or fall as daily life activity. To this aim, an efficient machine learning-based fall detection algorithm has been proposed in this paper. The proposed algorithm detects fall with efficient sensitivity, specificity, and accuracy as compared to the state-of-the-art techniques. A publicly available dataset with a very simple and computationally efficient set of features is used to accurately detect the fall incident. The proposed algorithm reports and accuracy of 99.98% with the Support Vector Machine(SVM) classifier.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.11976v1
PDF	https://arxiv.org/pdf/1911.11976v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-machine-learning-based-elderly
Repo
Framework

An Inductive Synthesis Framework for Verifiable Reinforcement Learning


Title	An Inductive Synthesis Framework for Verifiable Reinforcement Learning
Authors	He Zhu, Zikang Xiong, Stephen Magill, Suresh Jagannathan
Abstract	Despite the tremendous advances that have been made in the last decade on developing useful machine-learning applications, their wider adoption has been hindered by the lack of strong assurance guarantees that can be made about their behavior. In this paper, we consider how formal verification techniques developed for traditional software systems can be repurposed for verification of reinforcement learning-enabled ones, a particularly important class of machine learning systems. Rather than enforcing safety by examining and altering the structure of a complex neural network implementation, our technique uses blackbox methods to synthesizes deterministic programs, simpler, more interpretable, approximations of the network that can nonetheless guarantee desired safety properties are preserved, even when the network is deployed in unanticipated or previously unobserved environments. Our methodology frames the problem of neural network verification in terms of a counterexample and syntax-guided inductive synthesis procedure over these programs. The synthesis procedure searches for both a deterministic program and an inductive invariant over an infinite state transition system that represents a specification of an application’s control logic. Additional specifications defining environment-based constraints can also be provided to further refine the search space. Synthesized programs deployed in conjunction with a neural network implementation dynamically enforce safety conditions by monitoring and preventing potentially unsafe actions proposed by neural policies. Experimental results over a wide range of cyber-physical applications demonstrate that software-inspired formal verification techniques can be used to realize trustworthy reinforcement learning systems with low overhead.
Tasks
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07273v1
PDF	https://arxiv.org/pdf/1907.07273v1.pdf
PWC	https://paperswithcode.com/paper/an-inductive-synthesis-framework-for
Repo
Framework

Towards Efficient Discriminative Pattern Mining in Hybrid Domains


Title	Towards Efficient Discriminative Pattern Mining in Hybrid Domains
Authors	Yoshitaka Kameya
Abstract	Discriminative pattern mining is a data mining task in which we find patterns that distinguish transactions in the class of interest from those in other classes, and is also called emerging pattern mining or subgroup discovery. One practical problem in discriminative pattern mining is how to handle numeric values in the input dataset. In this paper, we propose an algorithm for discriminative pattern mining that can deal with a transactional dataset in a hybrid domain, i.e. the one that includes both symbolic and numeric values. We also show the execution results of a prototype implementation of the proposed algorithm for two standard benchmark datasets.
Tasks
Published	2019-08-15
URL	https://arxiv.org/abs/1908.06801v1
PDF	https://arxiv.org/pdf/1908.06801v1.pdf
PWC	https://paperswithcode.com/paper/towards-efficient-discriminative-pattern
Repo
Framework