January 26, 2020

3383 words 16 mins read

Paper Group ANR 1607

ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths. Deep Hashing for Signed Social Network Embedding. Orchestrating Development Lifecycle of Machine Learning Based IoT Applications: A Survey. Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions. Inference of a mesoscopic population …

ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths


Title	ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
Authors	Yanhao Zhu, Zhineng Chen, Shuai Zhao, Hongtao Xie, Wenming Guo, Yongdong Zhang
Abstract	Nowadays U-net-like FCNs predominate various biomedical image segmentation applications and attain promising performance, largely due to their elegant architectures, e.g., symmetric contracting and expansive paths as well as lateral skip-connections. It remains a research direction to devise novel architectures to further benefit the segmentation. In this paper, we develop an ACE-net that aims to enhance the feature representation and utilization by augmenting the contracting and expansive paths. In particular, we augment the paths by the recently proposed advanced techniques including ASPP, dense connection and deep supervision mechanisms, and novel connections such as directly connecting the raw image to the expansive side. With these augmentations, ACE-net can utilize features from multiple sources, scales and reception fields to segment while still maintains a relative simple architecture. Experiments on two typical biomedical segmentation tasks validate its effectiveness, where highly competitive results are obtained in both tasks while ACE-net still runs fast at inference.
Tasks	Semantic Segmentation
Published	2019-08-23
URL	https://arxiv.org/abs/1909.04148v1
PDF	https://arxiv.org/pdf/1909.04148v1.pdf
PWC	https://paperswithcode.com/paper/ace-net-biomedical-image-segmentation-with
Repo
Framework


Title	Deep Hashing for Signed Social Network Embedding
Authors	Jia-Nan Guo, Xian-Ling Mao, Xiao-Jian Jiang, Ying-Xiang Sun, Wei Wei, He-Yan Huang
Abstract	Network embedding is a promising way of network representation, facilitating many signed social network processing and analysis tasks such as link prediction and node classification. Recently, feature hashing has been adopted in several existing embedding algorithms to improve the efficiency, which has obtained a great success. However, the existing feature hashing based embedding algorithms only consider the positive links in signed social networks. Intuitively, negative links can also help improve the performance. Thus, in this paper, we propose a novel deep hashing method for signed social network embedding by considering simultaneously positive and negative links. Extensive experiments show that the proposed method performs better than several state-of-the-art baselines through link prediction task over two real-world signed social networks.
Tasks	Link Prediction, Network Embedding, Node Classification
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04007v3
PDF	https://arxiv.org/pdf/1908.04007v3.pdf
PWC	https://paperswithcode.com/paper/deep-kernel-supervised-hashing-for-network
Repo
Framework

Orchestrating Development Lifecycle of Machine Learning Based IoT Applications: A Survey


Title	Orchestrating Development Lifecycle of Machine Learning Based IoT Applications: A Survey
Authors	Bin Qian, Jie Su, Zhenyu Wen, Devki Nandan Jha, Yinhao Li, Yu Guan, Deepak Puthal, Philip James, Renyu Yang, Albert Y. Zomaya, Omer Rana, Lizhe Wang, Rajiv Ranjan
Abstract	Machine Learning (ML) and Internet of Things (IoT) are complementary advances: ML techniques unlock complete potentials of IoT with intelligence, and IoT applications increasingly feed data collected by sensors into ML models, thereby employing results to improve their business processes and services. Hence, orchestrating ML pipelines that encompasses model training and implication involved in holistic development lifecycle of an IoT application often leads to complex system integration. This paper provides a comprehensive and systematic survey on the development lifecycle of ML-based IoT application. We outline core roadmap and taxonomy, and subsequently assess and compare existing standard techniques used in individual stage.
Tasks
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05433v3
PDF	https://arxiv.org/pdf/1910.05433v3.pdf
PWC	https://paperswithcode.com/paper/orchestrating-development-lifecycle-of
Repo
Framework

Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions


Title	Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions
Authors	Can Chen, Luca Zanotti Fragonara, Antonios Tsourdos
Abstract	In order to achieve better performance for point cloud analysis, many researchers apply deeper neural networks using stacked Multi-Layer-Perceptron (MLP) convolutions over irregular point cloud. However, applying dense MLP convolutions over large amount of points (e.g. autonomous driving application) leads to inefficiency in memory and computation. To achieve high performance but less complexity, we propose a deep-wide neural network, called ShufflePointNet, to exploit fine-grained local features and reduce redundancy in parallel using group convolution and channel shuffle operation. Unlike conventional operation that directly applies MLPs on high-dimensional features of point cloud, our model goes wider by splitting features into groups in advance, and each group with certain smaller depth is only responsible for respective MLP operation, which can reduce complexity and allows to encode more useful information. Meanwhile, we connect communication between groups by shuffling groups in feature channel to capture fine-grained features. We claim that, multi-branch method for wider neural networks is also beneficial to feature extraction for point cloud. We present extensive experiments for shape classification task on ModelNet40 dataset and semantic segmentation task on large scale datasets ShapeNet part, S3DIS and KITTI. We further perform ablation study and compare our model to other state-of-the-art algorithms in terms of complexity and accuracy.
Tasks	Autonomous Driving, Semantic Segmentation
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10431v1
PDF	https://arxiv.org/pdf/1909.10431v1.pdf
PWC	https://paperswithcode.com/paper/190910431
Repo
Framework

Inference of a mesoscopic population model from population spike trains


Title	Inference of a mesoscopic population model from population spike trains
Authors	Alexandre René, André Longtin, Jakob H. Macke
Abstract	To understand how rich dynamics emerge in neural populations, we require models exhibiting a wide range of activity patterns while remaining interpretable in terms of connectivity and single-neuron dynamics. However, it has been challenging to fit such mechanistic spiking networks at the single neuron scale to empirical population data. To close this gap, we propose to fit such data at a meso scale, using a mechanistic but low-dimensional and hence statistically tractable model. The mesoscopic representation is obtained by approximating a population of neurons as multiple homogeneous `pools’ of neurons, and modelling the dynamics of the aggregate population activity within each pool. We derive the likelihood of both single-neuron and connectivity parameters given this activity, which can then be used to either optimize parameters by gradient ascent on the log-likelihood, or to perform Bayesian inference using Markov Chain Monte Carlo (MCMC) sampling. We illustrate this approach using a model of generalized integrate-and-fire neurons for which mesoscopic dynamics have been previously derived, and show that both single-neuron and connectivity parameters can be recovered from simulated data. In particular, our inference method extracts posterior correlations between model parameters, which define parameter subsets able to reproduce the data. We compute the Bayesian posterior for combinations of parameters using MCMC sampling and investigate how the approximations inherent to a mesoscopic population model impact the accuracy of the inferred single-neuron parameters. \|
Tasks	Bayesian Inference
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01618v2
PDF	https://arxiv.org/pdf/1910.01618v2.pdf
PWC	https://paperswithcode.com/paper/inference-of-a-mesoscopic-population-model
Repo
Framework

Bringing Belief Base Change into Dynamic Epistemic Logic


Title	Bringing Belief Base Change into Dynamic Epistemic Logic
Authors	Marlo Souza, Álvaro Moreira
Abstract	AGM’s belief revision is one of the main paradigms in the study of belief change operations. In this context, belief bases (prioritised bases) have been primarily used to specify the agent’s belief state. While the connection of iterated AGM-like operations and their encoding in dynamic epistemic logics have been studied before, few works considered how well-known postulates from iterated belief revision theory can be characterised by means of belief bases and their counterpart in dynamic epistemic logic. Particularly, it has been shown that some postulates can be characterised through transformations in priority graphs, while others may not be represented that way. This work investigates changes in the semantics of Dynamic Preference Logic that give rise to an appropriate syntactic representation for its models that allow us to represent and reason about iterated belief base change in this logic.
Tasks
Published	2019-12-22
URL	https://arxiv.org/abs/1912.10515v1
PDF	https://arxiv.org/pdf/1912.10515v1.pdf
PWC	https://paperswithcode.com/paper/bringing-belief-base-change-into-dynamic
Repo
Framework

Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning


Title	Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning
Authors	Inseok Oh, Seungeun Rho, Sangbin Moon, Seongho Son, Hyoil Lee, Jinyun Chung
Abstract	Reinforcement learning combined with deep neural networks has performed remarkably well in many genres of games recently. It has surpassed human-level performance in fixed game environments and turn-based two player board games. However, to the best of our knowledge, current research has yet to produce a result that has surpassed human-level performance in modern complex fighting games. This is due to the inherent difficulties with real-time fighting games, including: vast action spaces, action dependencies, and imperfect information. We overcame these challenges and made 1v1 battle AI agents for the commercial game “Blade & Soul”. The trained agents competed against five professional gamers and achieved a win rate of 62%. This paper presents a practical reinforcement learning method that includes a novel self-play curriculum and data skipping techniques. Through the curriculum, three different styles of agents were created by reward shaping and were trained against each other. Additionally, this paper suggests data skipping techniques that could increase data efficiency and facilitate explorations in vast spaces. Since our method can be generally applied to all two-player competitive games with vast action spaces, we anticipate its application to game development including level design and automated balancing.
Tasks	Board Games
Published	2019-04-08
URL	https://arxiv.org/abs/1904.03821v3
PDF	https://arxiv.org/pdf/1904.03821v3.pdf
PWC	https://paperswithcode.com/paper/creating-pro-level-ai-for-real-time-fighting
Repo
Framework

Belief dynamics extraction


Title	Belief dynamics extraction
Authors	Arun Kumar, Zhengwei Wu, Xaq Pitkow, Paul Schrater
Abstract	Animal behavior is not driven simply by its current observations, but is strongly influenced by internal states. Estimating the structure of these internal states is crucial for understanding the neural basis of behavior. In principle, internal states can be estimated by inverting behavior models, as in inverse model-based Reinforcement Learning. However, this requires careful parameterization and risks model-mismatch to the animal. Here we take a data-driven approach to infer latent states directly from observations of behavior, using a partially observable switching semi-Markov process. This process has two elements critical for capturing animal behavior: it captures non-exponential distribution of times between observations, and transitions between latent states depend on the animal’s actions, features that require more complex non-markovian models to represent. To demonstrate the utility of our approach, we apply it to the observations of a simulated optimal agent performing a foraging task, and find that latent dynamics extracted by the model has correspondences with the belief dynamics of the agent. Finally, we apply our model to identify latent states in the behaviors of monkey performing a foraging task, and find clusters of latent states that identify periods of time consistent with expectant waiting. This data-driven behavioral model will be valuable for inferring latent cognitive states, and thereby for measuring neural representations of those states.
Tasks
Published	2019-02-02
URL	http://arxiv.org/abs/1902.00673v1
PDF	http://arxiv.org/pdf/1902.00673v1.pdf
PWC	https://paperswithcode.com/paper/belief-dynamics-extraction
Repo
Framework

Transfer Learning in the Field of Renewable Energies – A Transfer Learning Framework Providing Power Forecasts Throughout the Lifecycle of Wind Farms After Initial Connection to the Electrical Grid


Title	Transfer Learning in the Field of Renewable Energies – A Transfer Learning Framework Providing Power Forecasts Throughout the Lifecycle of Wind Farms After Initial Connection to the Electrical Grid
Authors	Jens Schreiber
Abstract	In recent years, transfer learning gained particular interest in the field of vision and natural language processing. In the research field of vision, e.g., deep neural networks and transfer learning techniques achieve almost perfect classification scores within minutes. Nonetheless, these techniques are not yet widely applied in other domains. Therefore, this article identifies critical challenges and shows potential solutions for power forecasts in the field of renewable energies. It proposes a framework utilizing transfer learning techniques in wind power forecasts with limited or no historical data. On the one hand, this allows evaluating the applicability of transfer learning in the field of renewable energy. On the other hand, by developing automatic procedures, we assure that the proposed methods provide a framework that applies to domains in organic computing as well.
Tasks	Transfer Learning
Published	2019-06-03
URL	https://arxiv.org/abs/1906.01168v1
PDF	https://arxiv.org/pdf/1906.01168v1.pdf
PWC	https://paperswithcode.com/paper/transfer-learning-in-the-field-of-renewable
Repo
Framework

An End-to-End Foreground-Aware Network for Person Re-Identification


Title	An End-to-End Foreground-Aware Network for Person Re-Identification
Authors	Yiheng Liu, Wengang Zhou, Jianzhuang Liu, Guojun Qi, Qi Tian, Houqiang Li
Abstract	Person re-identification is a crucial task of identifying pedestrians of interest across multiple surveillance camera views. In person re-identification, a pedestrian is usually represented with features extracted from a rectangular image region that inevitably contains the scene background, which incurs ambiguity to distinguish different pedestrians and degrades the accuracy. To this end, we propose an end-to-end foreground-aware network to discriminate foreground from background by learning a soft mask for person re-identification. In our method, in addition to the pedestrian ID as supervision for foreground, we introduce the camera ID of each pedestrian image for background modeling. The foreground branch and the background branch are optimized collaboratively. By presenting a target attention loss, the pedestrian features extracted from the foreground branch become more insensitive to the backgrounds, which greatly reduces the negative impacts of changing backgrounds on matching an identical across different camera views. Notably, in contrast to existing methods, our approach does not require any additional dataset to train a human landmark detector or a segmentation model for locating the background regions. The experimental results conducted on three challenging datasets, i.e., Market-1501, DukeMTMC-reID, and MSMT17, demonstrate the effectiveness of our approach.
Tasks	Person Re-Identification
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11547v1
PDF	https://arxiv.org/pdf/1910.11547v1.pdf
PWC	https://paperswithcode.com/paper/an-end-to-end-foreground-aware-network-for
Repo
Framework

Cross-Domain Face Synthesis using a Controllable GAN


Title	Cross-Domain Face Synthesis using a Controllable GAN
Authors	Fania Mokhayeri, Kaveh Kamali, Eric Granger
Abstract	The performance of face recognition (FR) systems applied in video surveillance has been shown to improve when the design data is augmented through synthetic face generation. This is true, for instance, with pair-wise matchers (e.g., deep Siamese networks) that typically rely on a reference gallery with one still image per individual. However, generating synthetic images in the source domain may not improve the performance during operations due to the domain shift w.r.t. the target domain. Moreover, despite the emergence of Generative Adversarial Networks (GANs) for realistic synthetic generation, it is often difficult to control the conditions under which synthetic faces are generated. In this paper, a cross-domain face synthesis approach is proposed that integrates a new Controllable GAN (C-GAN). It employs an off-the-shelf 3D face model as a simulator to generate face images under various poses. The simulated images and noise are input to the C-GAN for realism refinement which employs an additional adversarial game as a third player to preserve the identity and specific facial attributes of the refined images. This allows generating realistic synthetic face images that reflects capture conditions in the target domain while controlling the GAN output to generate faces under desired pose conditions. Experiments were performed using videos from the Chokepoint and COX-S2V datasets, and a deep Siamese network for FR with a single reference still per person. Results indicate that the proposed approach can provide a higher level of accuracy compared to the current state-of-the-art approaches for synthetic data augmentation.
Tasks	Data Augmentation, Face Generation, Face Recognition
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14247v1
PDF	https://arxiv.org/pdf/1910.14247v1.pdf
PWC	https://paperswithcode.com/paper/cross-domain-face-synthesis-using-a
Repo
Framework

Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Poorly-Drawn Sketches


Title	Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Poorly-Drawn Sketches
Authors	Weihao Xia, Yujiu Yang, Jing-Hao Xue
Abstract	Image generation task has received increasing attention because of its wide application in security and entertainment. Sketch-based face generation brings more fun and better quality of image generation due to supervised interaction. However, When a sketch poorly aligned with the true face is given as input, existing supervised image-to-image translation methods often cannot generate acceptable photo-realistic face images. To address this problem, in this paper we propose Cali-Sketch, a poorly-drawn-sketch to photo-realistic-image generation method. Cali-Sketch explicitly models stroke calibration and image generation using two constituent networks: a Stroke Calibration Network (SCN), which calibrates strokes of facial features and enriches facial details while preserving the original intent features; and an Image Synthesis Network (ISN), which translates the calibrated and enriched sketches to photo-realistic face images. In this way, we manage to decouple a difficult cross-domain translation problem into two easier steps. Extensive experiments verify that the face photos generated by Cali-Sketch are both photo-realistic and faithful to the input sketches, compared with state-of-the-art methods
Tasks	Calibration, Face Generation, Image Generation, Image-to-Image Translation
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00426v1
PDF	https://arxiv.org/pdf/1911.00426v1.pdf
PWC	https://paperswithcode.com/paper/cali-sketch-stroke-calibration-and-completion
Repo
Framework

Incremental learning for the detection and classification of GAN-generated images


Title	Incremental learning for the detection and classification of GAN-generated images
Authors	Francesco Marra, Cristiano Saltori, Giulia Boato, Luisa Verdoliva
Abstract	Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new opportunities for the creative industry but, at the same time, new scary scenarios where such content can be maliciously misused. Therefore, it is essential to develop innovative methodologies to automatically tell apart real from computer generated multimedia, possibly able to follow the evolution and continuous improvement of data in terms of quality and realism. In the last few years, several deep learning-based solutions have been proposed for this problem, mostly based on Convolutional Neural Networks (CNNs). Although results are good in controlled conditions, it is not clear how such proposals can adapt to real-world scenarios, where learning needs to continuously evolve as new types of generated data appear. In this work, we tackle this problem by proposing an approach based on incremental learning for the detection and classification of GAN-generated images. Experiments on a dataset comprising images generated by several GAN-based architectures show that the proposed method is able to correctly perform discrimination when new GANs are presented to the network
Tasks	Face Generation
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01568v2
PDF	https://arxiv.org/pdf/1910.01568v2.pdf
PWC	https://paperswithcode.com/paper/incremental-learning-for-the-detection-and
Repo
Framework

Bi-Skip: A Motion Deblurring Network Using Self-paced Learning


Title	Bi-Skip: A Motion Deblurring Network Using Self-paced Learning
Authors	Yiwei Zhang, Chunbiao Zhu, Ge Li, Yuan Zhao, Haifeng Shen
Abstract	A fast and effective motion deblurring method has great application values in real life. This work presents an innovative approach in which a self-paced learning is combined with GAN to deblur image. First, We explain that a proper generator can be used as deep priors and point out that the solution for pixel-based loss is not same with the one for perception-based loss. By using these ideas as starting points, a Bi-Skip network is proposed to improve the generating ability and a bi-level loss is adopted to solve the problem that common conditions are non-identical. Second, considering that the complex motion blur will perturb the network in the training process, a self-paced mechanism is adopted to enhance the robustness of the network. Through extensive evaluations on both qualitative and quantitative criteria, it is demonstrated that our approach has a competitive advantage over state-of-the-art methods.
Tasks	Deblurring
Published	2019-02-24
URL	http://arxiv.org/abs/1902.08915v1
PDF	http://arxiv.org/pdf/1902.08915v1.pdf
PWC	https://paperswithcode.com/paper/bi-skip-a-motion-deblurring-network-using
Repo
Framework

A Deep Recurrent Q Network towards Self-adapting Distributed Microservices architecture


Title	A Deep Recurrent Q Network towards Self-adapting Distributed Microservices architecture
Authors	Basel Magableh
Abstract	One desired aspect of microservices architecture is the ability to self-adapt its own architecture and behaviour in response to changes in the operational environment. To achieve the desired high levels of self-adaptability, this research implements the distributed microservices architectures model, as informed by the MAPE-K model. The proposed architecture employs a multi adaptation agents supported by a centralised controller, that can observe the environment and execute a suitable adaptation action. The adaptation planning is managed by a deep recurrent Q-network (DRQN). It is argued that such integration between DRQN and MDP agents in a MAPE-K model offers distributed microservice architecture with self-adaptability and high levels of availability and scalability. Integrating DRQN into the adaptation process improves the effectiveness of the adaptation and reduces any adaptation risks, including resources over-provisioning and thrashing. The performance of DRQN is evaluated against deep Q-learning and policy gradient algorithms including: i) deep q-network (DQN), ii) dulling deep Q-network (DDQN), iii) a policy gradient neural network (PGNN), and iv) deep deterministic policy gradient (DDPG). The DRQN implementation in this paper manages to outperform the above mentioned algorithms in terms of total reward, less adaptation time, lower error rates, plus faster convergence and training times. We strongly believe that DRQN is more suitable for driving the adaptation in distributed services-oriented architecture and offers better performance than other dynamic decision-making algorithms.
Tasks	Decision Making, Q-Learning
Published	2019-01-13
URL	http://arxiv.org/abs/1901.04011v2
PDF	http://arxiv.org/pdf/1901.04011v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-recurrent-q-network-towards-self
Repo
Framework