January 28, 2020

3082 words 15 mins read

Paper Group ANR 822

3D Quantum Cuts for Automatic Segmentation of Porous Media in Tomography Images. Development of a Forecasting and Warning System on the Ecological Life-Cycle of Sunn Pest. Distilling On-Device Intelligence at the Network Edge. End-to-End Pore Extraction and Matching in Latent Fingerprints: Going Beyond Minutiae. Graph Neural Reasoning for 2-Quantif …

3D Quantum Cuts for Automatic Segmentation of Porous Media in Tomography Images


Title	3D Quantum Cuts for Automatic Segmentation of Porous Media in Tomography Images
Authors	Junaid Malik, Serkan Kiranyaz, Riyadh Al-Raoush, Olivier Monga, Patricia Garnier, Sebti Foufou, Abdelaziz Bouras, Alexandros Iosifidis, Moncef Gabbouj, Philippe C. Baveye
Abstract	Binary segmentation of volumetric images of porous media is a crucial step towards gaining a deeper understanding of the factors governing biogeochemical processes at minute scales. Contemporary work primarily revolves around primitive techniques based on global or local adaptive thresholding that have known common drawbacks in image segmentation. Moreover, absence of a unified benchmark prohibits quantitative evaluation, which further clouds the impact of existing methodologies. In this study, we tackle the issue on both fronts. Firstly, by drawing parallels with natural image segmentation, we propose a novel, and automatic segmentation technique, 3D Quantum Cuts (QCuts-3D) grounded on a state-of-the-art spectral clustering technique. Secondly, we curate and present a publicly available dataset of 68 multiphase volumetric images of porous media with diverse solid geometries, along with voxel-wise ground truth annotations for each constituting phase. We provide comparative evaluations between QCuts-3D and the current state-of-the-art over this dataset across a variety of evaluation metrics. The proposed systematic approach achieves a 26% increase in AUROC while achieving a substantial reduction of the computational complexity of the state-of-the-art competitors. Moreover, statistical analysis reveals that the proposed method exhibits significant robustness against the compositional variations of porous media.
Tasks	Semantic Segmentation
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04412v2
PDF	http://arxiv.org/pdf/1904.04412v2.pdf
PWC	https://paperswithcode.com/paper/3d-quantum-cuts-for-automatic-segmentation-of
Repo
Framework

Development of a Forecasting and Warning System on the Ecological Life-Cycle of Sunn Pest


Title	Development of a Forecasting and Warning System on the Ecological Life-Cycle of Sunn Pest
Authors	İsmail Balaban, Fatih Acun, Onur Yiğit Arpalı, Furkan Murat, Numan Ertuğrul Babaroğlu, Emre Akci, Mehmet Çulcu, Mümtaz Özkan, Selim Temizer
Abstract	We provide a machine learning solution that replaces the traditional methods for deciding the pesticide application time of Sunn Pest. We correlate climate data with phases of Sunn Pest in its life-cycle and decide whether the fields should be sprayed. Our solution includes two groups of prediction models. The first group contains decision trees that predict migration time of Sunn Pest from winter quarters to wheat fields. The second group contains random forest models that predict the nymphal stage percentages of Sunn Pest which is a criterion for pesticide application. We trained our models on four years of climate data which was collected from Kir\c{s}ehir and Aksaray. The experiments show that our promised solution make correct predictions with high accuracies.
Tasks
Published	2019-05-05
URL	https://arxiv.org/abs/1905.01640v1
PDF	https://arxiv.org/pdf/1905.01640v1.pdf
PWC	https://paperswithcode.com/paper/development-of-a-forecasting-and-warning
Repo
Framework

Distilling On-Device Intelligence at the Network Edge


Title	Distilling On-Device Intelligence at the Network Edge
Authors	Jihong Park, Shiqiang Wang, Anis Elgabli, Seungeun Oh, Eunjeong Jeong, Han Cha, Hyesung Kim, Seong-Lyun Kim, Mehdi Bennis
Abstract	Devices at the edge of wireless networks are the last mile data sources for machine learning (ML). As opposed to traditional ready-made public datasets, these user-generated private datasets reflect the freshest local environments in real time. They are thus indispensable for enabling mission-critical intelligent systems, ranging from fog radio access networks (RANs) to driverless cars and e-Health wearables. This article focuses on how to distill high-quality on-device ML models using fog computing, from such user-generated private data dispersed across wirelessly connected devices. To this end, we introduce communication-efficient and privacy-preserving distributed ML frameworks, termed fog ML (FML), wherein on-device ML models are trained by exchanging model parameters, model outputs, and surrogate data. We then present advanced FML frameworks addressing wireless RAN characteristics, limited on-device resources, and imbalanced data distributions. Our study suggests that the full potential of FML can be reached by co-designing communication and distributed ML operations while accounting for heterogeneous hardware specifications, data characteristics, and user requirements.
Tasks
Published	2019-08-16
URL	https://arxiv.org/abs/1908.05895v1
PDF	https://arxiv.org/pdf/1908.05895v1.pdf
PWC	https://paperswithcode.com/paper/distilling-on-device-intelligence-at-the
Repo
Framework

End-to-End Pore Extraction and Matching in Latent Fingerprints: Going Beyond Minutiae


Title	End-to-End Pore Extraction and Matching in Latent Fingerprints: Going Beyond Minutiae
Authors	Dinh-Luan Nguyen, Anil K. Jain
Abstract	Latent fingerprint recognition is not a new topic but it has attracted a lot of attention from researchers in both academia and industry over the past 50 years. With the rapid development of pattern recognition techniques, automated fingerprint identification systems (AFIS) have become more and more ubiquitous. However, most AFIS are utilized for live-scan or rolled/slap prints while only a few systems can work on latent fingerprints with reasonable accuracy. The question of whether taking higher resolution scans of latent fingerprints and their rolled/slap mate prints could help improve the identification accuracy still remains an open question in the forensic community. Because pores are one of the most reliable features besides minutiae to identify latent fingerprints, we propose an end-to-end automatic pore extraction and matching system to analyze the utility of pores in latent fingerprint identification. Hence, this paper answers two questions in the latent fingerprint domain: (i) does the incorporation of pores as level-3 features improve the system performance significantly? and (ii) does the 1,000 ppi image resolution improve the recognition results? We believe that our proposed end-to-end pore extraction and matching system will be a concrete baseline for future latent AFIS development.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11472v2
PDF	https://arxiv.org/pdf/1905.11472v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-pore-extraction-and-matching-in
Repo
Framework

Graph Neural Reasoning for 2-Quantified Boolean Formula Solvers


Title	Graph Neural Reasoning for 2-Quantified Boolean Formula Solvers
Authors	Zhanfu Yang, Fei Wang, Ziliang Chen, Guannan Wei, Tiark Rompf
Abstract	In this paper, we investigate the feasibility of learning GNN (Graph Neural Network) based solvers and GNN-based heuristics for specified QBF (Quantified Boolean Formula) problems. We design and evaluate several GNN architectures for 2QBF formulae, and conjecture that GNN has limitations in learning 2QBF solvers. Then we show how to learn a heuristic CEGAR 2QBF solver. We further explore generalizing GNN-based heuristics to larger unseen instances, and uncover some interesting challenges. In summary, this paper provides a comprehensive surveying view of applying GNN-embeddings to specified QBF solvers, and aims to offer guidance in applying ML to more complicated symbolic reasoning problems.
Tasks
Published	2019-04-27
URL	http://arxiv.org/abs/1904.12084v1
PDF	http://arxiv.org/pdf/1904.12084v1.pdf
PWC	https://paperswithcode.com/paper/graph-neural-reasoning-for-2-quantified
Repo
Framework

Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents


Title	Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agents
Authors	Xian Yeow Lee, Sambit Ghadai, Kai Liang Tan, Chinmay Hegde, Soumik Sarkar
Abstract	Robustness of Deep Reinforcement Learning (DRL) algorithms towards adversarial attacks in real world applications such as those deployed in cyber-physical systems (CPS) are of increasing concern. Numerous studies have investigated the mechanisms of attacks on the RL agent’s state space. Nonetheless, attacks on the RL agent’s action space (AS) (corresponding to actuators in engineering systems) are equally perverse; such attacks are relatively less studied in the ML literature. In this work, we first frame the problem as an optimization problem of minimizing the cumulative reward of an RL agent with decoupled constraints as the budget of attack. We propose a white-box Myopic Action Space (MAS) attack algorithm that distributes the attacks across the action space dimensions. Next, we reformulate the optimization problem above with the same objective function, but with a temporally coupled constraint on the attack budget to take into account the approximated dynamics of the agent. This leads to the white-box Look-ahead Action Space (LAS) attack algorithm that distributes the attacks across the action and temporal dimensions. Our results shows that using the same amount of resources, the LAS attack deteriorates the agent’s performance significantly more than the MAS attack. This reveals the possibility that with limited resource, an adversary can utilize the agent’s dynamics to malevolently craft attacks that causes the agent to fail. Additionally, we leverage these attack strategies as a possible tool to gain insights on the potential vulnerabilities of DRL agents.
Tasks
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02583v2
PDF	https://arxiv.org/pdf/1909.02583v2.pdf
PWC	https://paperswithcode.com/paper/spatiotemporally-constrained-action-space
Repo
Framework

Recurrent Attentive Neural Process for Sequential Data


Title	Recurrent Attentive Neural Process for Sequential Data
Authors	Shenghao Qin, Jiacheng Zhu, Jimmy Qin, Wenshuo Wang, Ding Zhao
Abstract	Neural processes (NPs) learn stochastic processes and predict the distribution of target output adaptively conditioned on a context set of observed input-output pairs. Furthermore, Attentive Neural Process (ANP) improved the prediction accuracy of NPs by incorporating attention mechanism among contexts and targets. In a number of real-world applications such as robotics, finance, speech, and biology, it is critical to learn the temporal order and recurrent structure from sequential data. However, the capability of NPs capturing these properties is limited due to its permutation invariance instinct. In this paper, we proposed the Recurrent Attentive Neural Process (RANP), or alternatively, Attentive Neural Process-RecurrentNeural Network(ANP-RNN), in which the ANP is incorporated into a recurrent neural network. The proposed model encapsulates both the inductive biases of recurrent neural networks and also the strength of NPs for modelling uncertainty. We demonstrate that RANP can effectively model sequential data and outperforms NPs and LSTMs remarkably in a 1D regression toy example as well as autonomous-driving applications.
Tasks	Autonomous Driving
Published	2019-10-17
URL	https://arxiv.org/abs/1910.09323v1
PDF	https://arxiv.org/pdf/1910.09323v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-attentive-neural-process-for
Repo
Framework

Don’t Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation


Title	Don’t Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation
Authors	Horia Porav, Tom Bruls, Paul Newman
Abstract	Modern models that perform system-critical tasks such as segmentation and localization exhibit good performance and robustness under ideal conditions (i.e. daytime, overcast) but performance degrades quickly and often catastrophically when input conditions change. In this work, we present a domain adaptation system that uses light-weight input adapters to pre-processes input images, irrespective of their appearance, in a way that makes them compatible with off-the-shelf computer vision tasks that are trained only on inputs with ideal conditions. No fine-tuning is performed on the off-the-shelf models, and the system is capable of incrementally training new input adapters in a self-supervised fashion, using the computer vision tasks as supervisors, when the input domain differs significantly from previously seen domains. We report large improvements in semantic segmentation and topological localization performance on two popular datasets, RobotCar and BDD.
Tasks	Domain Adaptation, Semantic Segmentation
Published	2019-07-25
URL	https://arxiv.org/abs/1907.11004v1
PDF	https://arxiv.org/pdf/1907.11004v1.pdf
PWC	https://paperswithcode.com/paper/dont-worry-about-the-weather-unsupervised
Repo
Framework

Learning Multi-Sense Word Distributions using Approximate Kullback-Leibler Divergence


Title	Learning Multi-Sense Word Distributions using Approximate Kullback-Leibler Divergence
Authors	P. Jayashree, Ballijepalli Shreya, P. K. Srijith
Abstract	Learning word representations has garnered greater attention in the recent past due to its diverse text applications. Word embeddings encapsulate the syntactic and semantic regularities of sentences. Modelling word embedding as multi-sense gaussian mixture distributions, will additionally capture uncertainty and polysemy of words. We propose to learn the Gaussian mixture representation of words using a Kullback-Leibler (KL) divergence based objective function. The KL divergence based energy function provides a better distance metric which can effectively capture entailment and distribution similarity among the words. Due to the intractability of KL divergence for Gaussian mixture, we go for a KL approximation between Gaussian mixtures. We perform qualitative and quantitative experiments on benchmark word similarity and entailment datasets which demonstrate the effectiveness of the proposed approach.
Tasks	Word Embeddings
Published	2019-11-12
URL	https://arxiv.org/abs/1911.06118v1
PDF	https://arxiv.org/pdf/1911.06118v1.pdf
PWC	https://paperswithcode.com/paper/learning-multi-sense-word-distributions-using
Repo
Framework

Learning and Reasoning for Robot Sequential Decision Making under Uncertainty


Title	Learning and Reasoning for Robot Sequential Decision Making under Uncertainty
Authors	Saeid Amiri, Mohammad Shokrolah Shirazi, Shiqi Zhang
Abstract	Robots frequently face complex tasks that require more than one action, where sequential decision-making (SDM) capabilities become necessary. The key contribution of this work is a robot SDM framework, called LCORPP, that supports the simultaneous capabilities of supervised learning for passive state estimation, automated reasoning with declarative human knowledge, and planning under uncertainty toward achieving long-term goals. In particular, we use a hybrid reasoning paradigm to refine the state estimator, and provide informative priors for the probabilistic planner. In experiments, a mobile robot is tasked with estimating human intentions using their motion trajectories, declarative contextual knowledge, and human-robot interaction (dialog-based and motion-based). Results suggest that, in efficiency and accuracy, our framework performs better than its no-learning and no-reasoning counterparts in office environment.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2019-01-16
URL	https://arxiv.org/abs/1901.05322v3
PDF	https://arxiv.org/pdf/1901.05322v3.pdf
PWC	https://paperswithcode.com/paper/robot-sequential-decision-making-using-lstm
Repo
Framework

Efficient non-conjugate Gaussian process factor models for spike count data using polynomial approximations


Title	Efficient non-conjugate Gaussian process factor models for spike count data using polynomial approximations
Authors	Stephen L. Keeley, David M. Zoltowski, Yiyi Yu, Jacob L. Yates, Spencer L. Smith, Jonathan W. Pillow
Abstract	Gaussian Process Factor Analysis (GPFA) has been broadly applied to the problem of identifying smooth, low-dimensional temporal structure underlying large-scale neural recordings. However, spike trains are non-Gaussian, which motivates combining GPFA with discrete observation models for binned spike count data. The drawback to this approach is that GPFA priors are not conjugate to count model likelihoods, which makes inference challenging. Here we address this obstacle by introducing a fast, approximate inference method for non-conjugate GPFA models. Our approach uses orthogonal second-order polynomials to approximate the nonlinear terms in the non-conjugate log-likelihood, resulting in a method we refer to as polynomial approximate log-likelihood (PAL) estimators. This approximation allows for accurate closed-form evaluation of marginal likelihood and fast numerical optimization for parameters and hyperparameters. We derive PAL estimators for GPFA models with binomial, Poisson, and negative binomial observations, and additionally show that the parameters obtained can be used to initialize black-box variational inference, which significantly speeds up and stabilizes the inference procedure for these factor analytic models. We apply these methods to data from mouse visual cortex and monkey higher-order visual and parietal cortices, and compare GPFA under three different spike count observation models to traditional GPFA. We demonstrate that PAL estimators achieve fast and accurate extraction of latent structure from multi-neuron spike train data.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03318v1
PDF	https://arxiv.org/pdf/1906.03318v1.pdf
PWC	https://paperswithcode.com/paper/efficient-non-conjugate-gaussian-process
Repo
Framework

Non-uniqueness phenomenon of object representation in modelling IT cortex by deep convolutional neural network (DCNN)


Title	Non-uniqueness phenomenon of object representation in modelling IT cortex by deep convolutional neural network (DCNN)
Authors	Qiulei Dong, Bo Liu, Zhanyi Hu
Abstract	Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modelling approach for neural object representation in primate inferotemporal cortex. In this work, we show that some inherent non-uniqueness problem exists in the DCNN-based modelling of image object representations. This non-uniqueness phenomenon reveals to some extent the theoretical limitation of this general modelling approach, and invites due attention to be taken in practice.
Tasks
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02487v1
PDF	https://arxiv.org/pdf/1906.02487v1.pdf
PWC	https://paperswithcode.com/paper/non-uniqueness-phenomenon-of-object
Repo
Framework

Self Training Autonomous Driving Agent


Title	Self Training Autonomous Driving Agent
Authors	Shashank Kotyan, Danilo Vasconcellos Vargas, Venkanna U
Abstract	Intrinsically, driving is a Markov Decision Process which suits well the reinforcement learning paradigm. In this paper, we propose a novel agent which learns to drive a vehicle without any human assistance. We use the concept of reinforcement learning and evolutionary strategies to train our agent in a 2D simulation environment. Our model’s architecture goes beyond the World Model’s by introducing difference images in the auto encoder. This novel involvement of difference images in the auto-encoder gives better representation of the latent space with respect to the motion of vehicle and helps an autonomous agent to learn more efficiently how to drive a vehicle. Results show that our method requires fewer (96% less) total agents, (87.5% less) agents per generations, (70% less) generations and (90% less) rollouts than the original architecture while achieving the same accuracy of the original.
Tasks	Autonomous Driving
Published	2019-04-26
URL	http://arxiv.org/abs/1904.12738v1
PDF	http://arxiv.org/pdf/1904.12738v1.pdf
PWC	https://paperswithcode.com/paper/self-training-autonomous-driving-agent
Repo
Framework

Hybrid Cosine Based Convolutional Neural Networks


Title	Hybrid Cosine Based Convolutional Neural Networks
Authors	Adrià Ciurana, Albert Mosella-Montoro, Javier Ruiz-Hidalgo
Abstract	Convolutional neural networks (CNNs) have demonstrated their capability to solve different kind of problems in a very huge number of applications. However, CNNs are limited for their computational and storage requirements. These limitations make difficult to implement these kind of neural networks on embedded devices such as mobile phones, smart cameras or advanced driving assistance systems. In this paper, we present a novel layer named Hybrid Cosine Based Convolution that replaces standard convolutional layers using cosine basis to generate filter weights. The proposed layers provide several advantages: faster convergence in training, the receptive field can be increased at no cost and substantially reduce the number of parameters. We evaluate our proposed layers on three competitive classification tasks where our proposed layers can achieve similar (and in some cases better) performances than VGG and ResNet architectures.
Tasks
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01987v1
PDF	http://arxiv.org/pdf/1904.01987v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-cosine-based-convolutional-neural
Repo
Framework

TexturePose: Supervising Human Mesh Estimation with Texture Consistency


Title	TexturePose: Supervising Human Mesh Estimation with Texture Consistency
Authors	Georgios Pavlakos, Nikos Kolotouros, Kostas Daniilidis
Abstract	This work addresses the problem of model-based human pose estimation. Recent approaches have made significant progress towards regressing the parameters of parametric human body models directly from images. Because of the absence of images with 3D shape ground truth, relevant approaches rely on 2D annotations or sophisticated architecture designs. In this work, we advocate that there are more cues we can leverage, which are available for free in natural images, i.e., without getting more annotations, or modifying the network architecture. We propose a natural form of supervision, that capitalizes on the appearance constancy of a person among different frames (or viewpoints). This seemingly insignificant and often overlooked cue goes a long way for model-based pose estimation. The parametric model we employ allows us to compute a texture map for each frame. Assuming that the texture of the person does not change dramatically between frames, we can apply a novel texture consistency loss, which enforces that each point in the texture map has the same texture value across all frames. Since the texture is transferred in this common texture map space, no camera motion computation is necessary, or even an assumption of smoothness among frames. This makes our proposed supervision applicable in a variety of settings, ranging from monocular video, to multi-view images. We benchmark our approach against strong baselines that require the same or even more annotations that we do and we consistently outperform them. Simultaneously, we achieve state-of-the-art results among model-based pose estimation approaches in different benchmarks. The project website with videos, results, and code can be found at https://seas.upenn.edu/~pavlakos/projects/texturepose.
Tasks	Pose Estimation
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11322v1
PDF	https://arxiv.org/pdf/1910.11322v1.pdf
PWC	https://paperswithcode.com/paper/texturepose-supervising-human-mesh-estimation-1
Repo
Framework