October 19, 2019

2663 words 13 mins read

Paper Group ANR 338

Problem-Adapted Artificial Intelligence for Online Network Optimization. TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation. A Missing Information Loss function for implicit feedback datasets. Non-rigid 3D Shape Registration using an Adaptive Template. Controllable Semantic Image Inpainting. Advances in Experience Replay. The …

Problem-Adapted Artificial Intelligence for Online Network Optimization


Title	Problem-Adapted Artificial Intelligence for Online Network Optimization
Authors	Spyridon Vassilaras, Luigi Vigneri, Nikolaos Liakopoulos, Georgios S. Paschos, Apostolos Destounis, Thrasyvoulos Spyropoulos, Merouane Debbah
Abstract	Future 5G wireless networks will rely on agile and automated network management, where the usage of diverse resources must be jointly optimized with surgical accuracy. A number of key wireless network functionalities (e.g., traffic steering, power control) give rise to hard optimization problems. What is more, high spatio-temporal traffic variability coupled with the need to satisfy strict per slice/service SLAs in modern networks, suggest that these problems must be constantly (re-)solved, to maintain close-to-optimal performance. To this end, we propose the framework of Online Network Optimization (ONO), which seeks to maintain both agile and efficient control over time, using an arsenal of data-driven, online learning, and AI-based techniques. Since the mathematical tools and the studied regimes vary widely among these methodologies, a theoretical comparison is often out of reach. Therefore, the important question `what is the right ONO technique?’ remains open to date. In this paper, we discuss the pros and cons of each technique and present a direct quantitative comparison for a specific use case, using real data. Our results suggest that carefully combining the insights of problem modeling with state-of-the-art AI techniques provides significant advantages at reasonable complexity. \|
Tasks
Published	2018-05-30
URL	http://arxiv.org/abs/1805.12090v2
PDF	http://arxiv.org/pdf/1805.12090v2.pdf
PWC	https://paperswithcode.com/paper/model-driven-artificial-intelligence-for
Repo
Framework

TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation


Title	TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation
Authors	Kai Yue, Lei Yang, Ruirui Li, Wei Hu, Fan Zhang, Wei Li
Abstract	For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions. Recently, convolutional neural networks (CNNs) have shown outstanding performance on this task. Although many deep neural network structures and techniques have been applied to improve the accuracy, few have paid attention to better differentiating the easily confused classes. In this paper, we propose TreeSegNet which adopts an adaptive network to increase the classification rate at the pixelwise level. Specifically, based on the infrastructure of DeepUNet, a Tree-CNN block in which each node represents a ResNeXt unit is constructed adaptively according to the confusion matrix and the proposed TreeCutting algorithm. By transporting feature maps through concatenating connections, the Tree-CNN block fuses multiscale features and learns best weights for the model. In experiments on the ISPRS 2D semantic labeling Potsdam dataset, the results obtained by TreeSegNet are better than those of other published state-of-the-art methods. Detailed comparison and analysis show that the improvement brought by the adaptive Tree-CNN block is significant.
Tasks	Semantic Segmentation
Published	2018-04-29
URL	http://arxiv.org/abs/1804.10879v2
PDF	http://arxiv.org/pdf/1804.10879v2.pdf
PWC	https://paperswithcode.com/paper/treesegnet-adaptive-tree-cnns-for
Repo
Framework

A Missing Information Loss function for implicit feedback datasets


Title	A Missing Information Loss function for implicit feedback datasets
Authors	Juan Arévalo, Juan Ramón Duque, Marco Creatura
Abstract	Latent factor models for Recommender Systems with implicit feedback typically treat unobserved user-item interactions (i.e. missing information) as negative feedback. This is frequently done either through negative sampling (point–wise loss) or with a ranking loss function (pair– or list–wise estimation). Since a zero preference recommendation is a valid solution for most common objective functions, regarding unknown values as actual zeros results in users having a zero preference recommendation for most of the available items. In this paper we propose a novel objective function, the \emph{Missing Information Loss} (MIL), that explicitly forbids treating unobserved user-item interactions as positive or negative feedback. We apply this loss to both traditional Matrix Factorization and user–based Denoising Autoencoder, and compare it with other established objective functions such as cross-entropy (both point- and pair-wise) or the recently proposed multinomial log-likelihood. MIL achieves competitive performance in ranking-aware metrics when applied to three datasets. Furthermore, we show that such a relevance in the recommendation is obtained while displaying popular items less frequently (up to a $20 %$ decrease with respect to the best competing method). This debiasing from the recommendation of popular items favours the appearance of infrequent items (up to a $50 %$ increase of long-tail recommendations), a valuable feature for Recommender Systems with a large catalogue of products.
Tasks	Denoising, Recommendation Systems
Published	2018-04-30
URL	http://arxiv.org/abs/1805.00121v2
PDF	http://arxiv.org/pdf/1805.00121v2.pdf
PWC	https://paperswithcode.com/paper/a-missing-information-loss-function-for
Repo
Framework

Non-rigid 3D Shape Registration using an Adaptive Template


Title	Non-rigid 3D Shape Registration using an Adaptive Template
Authors	Hang Dai, Nick Pears, William Smith
Abstract	We present a new fully-automatic non-rigid 3D shape registration (morphing) framework comprising (1) a new 3D landmarking and pose normalisation method; (2) an adaptive shape template method to accelerate the convergence of registration algorithms and achieve a better final shape correspondence and (3) a new iterative registration method that combines Iterative Closest Points with Coherent Point Drift (CPD) to achieve a more stable and accurate correspondence establishment than standard CPD. We call this new morphing approach Iterative Coherent Point Drift (ICPD). Our proposed framework is evaluated qualitatively and quantitatively on three datasets and compared with several other methods. The proposed framework is shown to give state-of-the-art performance.
Tasks
Published	2018-03-21
URL	http://arxiv.org/abs/1803.07973v2
PDF	http://arxiv.org/pdf/1803.07973v2.pdf
PWC	https://paperswithcode.com/paper/non-rigid-3d-shape-registration-using-an
Repo
Framework

Controllable Semantic Image Inpainting


Title	Controllable Semantic Image Inpainting
Authors	Jin Xu, Yee Whye Teh
Abstract	We develop a method for user-controllable semantic image inpainting: Given an arbitrary set of observed pixels, the unobserved pixels can be imputed in a user-controllable range of possibilities, each of which is semantically coherent and locally consistent with the observed pixels. We achieve this using a deep generative model bringing together: an encoder which can encode an arbitrary set of observed pixels, latent variables which are trained to represent disentangled factors of variations, and a bidirectional PixelCNN model. We experimentally demonstrate that our method can generate plausible inpainting results matching the user-specified semantics, but is still coherent with observed pixels. We justify our choices of architecture and training regime through more experiments.
Tasks	Image Inpainting
Published	2018-06-15
URL	http://arxiv.org/abs/1806.05953v1
PDF	http://arxiv.org/pdf/1806.05953v1.pdf
PWC	https://paperswithcode.com/paper/controllable-semantic-image-inpainting
Repo
Framework

Advances in Experience Replay


Title	Advances in Experience Replay
Authors	Tracy Wan, Neil Xu
Abstract	This project combines recent advances in experience replay techniques, namely, Combined Experience Replay (CER), Prioritized Experience Replay (PER), and Hindsight Experience Replay (HER). We show the results of combinations of these techniques with DDPG and DQN methods. CER always adds the most recent experience to the batch. PER chooses which experiences should be replayed based on how beneficial they will be towards learning. HER learns from failure by substituting the desired goal with the achieved goal and recomputing the reward function. The effectiveness of combinations of these experience replay techniques is tested in a variety of OpenAI gym environments.
Tasks
Published	2018-05-15
URL	http://arxiv.org/abs/1805.05536v1
PDF	http://arxiv.org/pdf/1805.05536v1.pdf
PWC	https://paperswithcode.com/paper/advances-in-experience-replay
Repo
Framework

Theoretical Analysis of Image-to-Image Translation with Adversarial Learning


Title	Theoretical Analysis of Image-to-Image Translation with Adversarial Learning
Authors	Xudong Pan, Mi Zhang, Daizong Ding
Abstract	Recently, a unified model for image-to-image translation tasks within adversarial learning framework has aroused widespread research interests in computer vision practitioners. Their reported empirical success however lacks solid theoretical interpretations for its inherent mechanism. In this paper, we reformulate their model from a brand-new geometrical perspective and have eventually reached a full interpretation on some interesting but unclear empirical phenomenons from their experiments. Furthermore, by extending the definition of generalization for generative adversarial nets to a broader sense, we have derived a condition to control the generalization capability of their model. According to our derived condition, several practical suggestions have also been proposed on model design and dataset construction as a guidance for further empirical researches.
Tasks	Image-to-Image Translation
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07001v1
PDF	http://arxiv.org/pdf/1806.07001v1.pdf
PWC	https://paperswithcode.com/paper/theoretical-analysis-of-image-to-image
Repo
Framework

Unsupervised Deep Context Prediction for Background Foreground Separation


Title	Unsupervised Deep Context Prediction for Background Foreground Separation
Authors	Maryam Sultana, Arif Mahmood, Sajid Javed, Soon Ki Jung
Abstract	In many advanced video based applications background modeling is a pre-processing step to eliminate redundant data, for instance in tracking or video surveillance applications. Over the past years background subtraction is usually based on low level or hand-crafted features such as raw color components, gradients, or local binary patterns. The background subtraction algorithms performance suffer in the presence of various challenges such as dynamic backgrounds, photometric variations, camera jitters, and shadows. To handle these challenges for the purpose of accurate background modeling we propose a unified framework based on the algorithm of image inpainting. It is an unsupervised visual feature learning hybrid Generative Adversarial algorithm based on context prediction. We have also presented the solution of random region inpainting by the fusion of center region inpaiting and random region inpainting with the help of poisson blending technique. Furthermore we also evaluated foreground object detection with the fusion of our proposed method and morphological operations. The comparison of our proposed method with 12 state-of-the-art methods shows its stability in the application of background estimation and foreground detection.
Tasks	Image Inpainting, Object Detection
Published	2018-05-21
URL	http://arxiv.org/abs/1805.07903v1
PDF	http://arxiv.org/pdf/1805.07903v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-deep-context-prediction-for
Repo
Framework

The Concept of the Deep Learning-Based System “Artificial Dispatcher” to Power System Control and Dispatch


Title	The Concept of the Deep Learning-Based System “Artificial Dispatcher” to Power System Control and Dispatch
Authors	Nikita Tomin, Victor Kurbatsky, Michael Negnevitsky
Abstract	Year by year control of normal and emergency conditions of up-to-date power systems becomes an increasingly complicated problem. With the increasing complexity the existing control system of power system conditions which includes operative actions of the dispatcher and work of special automatic devices proves to be insufficiently effective more and more frequently, which raises risks of dangerous and emergency conditions in power systems. The paper is aimed at compensating for the shortcomings of man (a cognitive barrier, exposure to stresses and so on) and automatic devices by combining their strong points, i.e. the dispatcher’s intelligence and the speed of automatic devices by virtue of development of the intelligent system “Artificial dispatcher” on the basis of deep machine learning technology. For realization of the system “Artificial dispatcher” in addition to deep learning it is planned to attract the game theory approaches to formalize work of the up-to-date power system as a game problem. The “gain” for “Artificial dispatcher” will consist in bringing in a power system in the normal steady-state or post-emergency conditions by means of the required control actions.
Tasks
Published	2018-05-07
URL	http://arxiv.org/abs/1805.05408v1
PDF	http://arxiv.org/pdf/1805.05408v1.pdf
PWC	https://paperswithcode.com/paper/the-concept-of-the-deep-learning-based-system
Repo
Framework

Accelerating Deep Neural Networks with Spatial Bottleneck Modules


Title	Accelerating Deep Neural Networks with Spatial Bottleneck Modules
Authors	Junran Peng, Lingxi Xie, Zhaoxiang Zhang, Tieniu Tan, Jingdong Wang
Abstract	This paper presents an efficient module named spatial bottleneck for accelerating the convolutional layers in deep neural networks. The core idea is to decompose convolution into two stages, which first reduce the spatial resolution of the feature map, and then restore it to the desired size. This operation decreases the sampling density in the spatial domain, which is independent yet complementary to network acceleration approaches in the channel domain. Using different sampling rates, we can tradeoff between recognition accuracy and model complexity. As a basic building block, spatial bottleneck can be used to replace any single convolutional layer, or the combination of two convolutional layers. We empirically verify the effectiveness of spatial bottleneck by applying it to the deep residual networks. Spatial bottleneck achieves 2x and 1.4x speedup on the regular and channel-bottlenecked residual blocks, respectively, with the accuracies retained in recognizing low-resolution images, and even improved in recognizing high-resolution images.
Tasks
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02601v1
PDF	http://arxiv.org/pdf/1809.02601v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-deep-neural-networks-with
Repo
Framework

Guided Upsampling Network for Real-Time Semantic Segmentation


Title	Guided Upsampling Network for Real-Time Semantic Segmentation
Authors	Davide Mazzini
Abstract	Semantic segmentation architectures are mainly built upon an encoder-decoder structure. These models perform subsequent downsampling operations in the encoder. Since operations on high-resolution activation maps are computationally expensive, usually the decoder produces output segmentation maps by upsampling with parameters-free operators like bilinear or nearest-neighbor. We propose a Neural Network named Guided Upsampling Network which consists of a multiresolution architecture that jointly exploits high-resolution and large context information. Then we introduce a new module named Guided Upsampling Module (GUM) that enriches upsampling operators by introducing a learnable transformation for semantic maps. It can be plugged into any existing encoder-decoder architecture with little modifications and low additional computation cost. We show with quantitative and qualitative experiments how our network benefits from the use of GUM module. A comprehensive set of experiments on the publicly available Cityscapes dataset demonstrates that Guided Upsampling Network can efficiently process high-resolution images in real-time while attaining state-of-the art performances.
Tasks	Real-Time Semantic Segmentation, Semantic Segmentation
Published	2018-07-19
URL	http://arxiv.org/abs/1807.07466v1
PDF	http://arxiv.org/pdf/1807.07466v1.pdf
PWC	https://paperswithcode.com/paper/guided-upsampling-network-for-real-time
Repo
Framework

Lehmer Transform and its Theoretical Properties


Title	Lehmer Transform and its Theoretical Properties
Authors	Masoud Ataei, Shengyuan Chen, Xiaogang Wang
Abstract	We propose a new class of transforms that we call {\it Lehmer Transform} which is motivated by the {\it Lehmer mean function}. The proposed {\it Lehmer transform} decomposes a function of a sample into their constituting statistical moments. Theoretical properties of the proposed transform are presented. This transform could be very useful to provide an alternative method in analyzing non-stationary signals such as brain wave EEG.
Tasks	EEG
Published	2018-05-13
URL	http://arxiv.org/abs/1805.04927v1
PDF	http://arxiv.org/pdf/1805.04927v1.pdf
PWC	https://paperswithcode.com/paper/lehmer-transform-and-its-theoretical
Repo
Framework

Generative adversarial networks for generation and classification of physical rehabilitation movement episodes


Title	Generative adversarial networks for generation and classification of physical rehabilitation movement episodes
Authors	L. Li, A. Vakanski
Abstract	This article proposes a method for mathematical modeling of human movements related to patient exercise episodes performed during physical therapy sessions by using artificial neural networks. The generative adversarial network structure is adopted, whereby a discriminative and a generative model are trained concurrently in an adversarial manner. Different network architectures are examined, with the discriminative and generative models structured as deep subnetworks of hidden layers comprised of convolutional or recurrent computational units. The models are validated on a data set of human movements recorded with an optical motion tracker. The results demonstrate an ability of the networks for classification of new instances of motions, and for generation of motion examples that resemble the recorded motion sequences.
Tasks
Published	2018-12-15
URL	http://arxiv.org/abs/1812.06307v1
PDF	http://arxiv.org/pdf/1812.06307v1.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-networks-for-4
Repo
Framework

FusedLSTM: Fusing frame-level and video-level features for Content-based Video Relevance Prediction


Title	FusedLSTM: Fusing frame-level and video-level features for Content-based Video Relevance Prediction
Authors	Yash Bhalgat
Abstract	This paper describes two of my best performing approaches on the Content-based Video Relevance Prediction challenge. In the FusedLSTM based approach, the inception-pool3 and the C3D-pool5 features are combined using an LSTM and a dense layer to form embeddings with the objective to minimize the triplet loss function. In the second approach, an Online Kernel Similarity Learning method is proposed to learn a non-linear similarity measure to adhere the relevance training data. The last section gives a complete comparison of all the approaches implemented during this challenge, including the one presented in the baseline paper.
Tasks
Published	2018-09-29
URL	http://arxiv.org/abs/1810.00136v1
PDF	http://arxiv.org/pdf/1810.00136v1.pdf
PWC	https://paperswithcode.com/paper/fusedlstm-fusing-frame-level-and-video-level
Repo
Framework

Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples


Title	Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples
Authors	Jake Zhao, Kyunghyun Cho
Abstract	We propose a retrieval-augmented convolutional network and propose to train it with local mixup, a novel variant of the recently proposed mixup algorithm. The proposed hybrid architecture combining a convolutional network and an off-the-shelf retrieval engine was designed to mitigate the adverse effect of off-manifold adversarial examples, while the proposed local mixup addresses on-manifold ones by explicitly encouraging the classifier to locally behave linearly on the data manifold. Our evaluation of the proposed approach against five readily-available adversarial attacks on three datasets–CIFAR-10, SVHN and ImageNet–demonstrate the improved robustness compared to the vanilla convolutional network.
Tasks
Published	2018-02-26
URL	http://arxiv.org/abs/1802.09502v1
PDF	http://arxiv.org/pdf/1802.09502v1.pdf
PWC	https://paperswithcode.com/paper/retrieval-augmented-convolutional-neural
Repo
Framework