Paper Group ANR 722
Solving $\ell^p!$-norm regularization with tensor kernels. Deep Learning for automatic sale receipt understanding. Gaussian Filter in CRF Based Semantic Segmentation. Q-Learning Algorithm for VoLTE Closed-Loop Power Control in Indoor Small Cells. Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks. Learning to segment on tiny …
Solving $\ell^p!$-norm regularization with tensor kernels
| Title | Solving $\ell^p!$-norm regularization with tensor kernels |
| Authors | Saverio Salzo, Johan A. K. Suykens, Lorenzo Rosasco |
| Abstract | In this paper, we discuss how a suitable family of tensor kernels can be used to efficiently solve nonparametric extensions of $\ell^p$ regularized learning methods. Our main contribution is proposing a fast dual algorithm, and showing that it allows to solve the problem efficiently. Our results contrast recent findings suggesting kernel methods cannot be extended beyond Hilbert setting. Numerical experiments confirm the effectiveness of the method. |
| Tasks | |
| Published | 2017-07-18 |
| URL | http://arxiv.org/abs/1707.05609v2 |
| http://arxiv.org/pdf/1707.05609v2.pdf | |
| PWC | https://paperswithcode.com/paper/solving-ellp-norm-regularization-with-tensor |
| Repo | |
| Framework | |
Deep Learning for automatic sale receipt understanding
| Title | Deep Learning for automatic sale receipt understanding |
| Authors | Rizlène Raoui-Outach, Cécile Million-Rousseau, Alexandre Benoit, Patrick Lambert |
| Abstract | As a general rule, data analytics are now mandatory for companies. Scanned document analysis brings additional challenges introduced by paper damages and scanning quality.In an industrial context, this work focuses on the automatic understanding of sale receipts which enable access to essential and accurate consumption statistics. Given an image acquired with a smart-phone, the proposed work mainly focuses on the first steps of the full tool chain which aims at providing essential information such as the store brand, purchased products and related prices with the highest possible confidence. To get this high confidence level, even if scanning is not perfectly controlled, we propose a double check processing tool-chain using Deep Convolutional Neural Networks (DCNNs) on one hand and more classical image and text processings on another hand.The originality of this work relates in this double check processing and in the joint use of DCNNs for different applications and text analysis. |
| Tasks | |
| Published | 2017-12-05 |
| URL | http://arxiv.org/abs/1712.01606v1 |
| http://arxiv.org/pdf/1712.01606v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-automatic-sale-receipt |
| Repo | |
| Framework | |
Gaussian Filter in CRF Based Semantic Segmentation
| Title | Gaussian Filter in CRF Based Semantic Segmentation |
| Authors | Yichi Gu, Qisheng Wu, Jing Li, Kai Cheng |
| Abstract | Artificial intelligence is making great changes in academy and industry with the fast development of deep learning, which is a branch of machine learning and statistical learning. Fully convolutional network [1] is the standard model for semantic segmentation. Conditional random fields coded as CNN [2] or RNN [3] and connected with FCN has been successfully applied in object detection [4]. In this paper, we introduce a multi-resolution neural network for FCN and apply Gaussian filter to the extended CRF kernel neighborhood and the label image to reduce the oscillating effect of CRF neural network segmentation, thus achieve higher precision and faster training speed. |
| Tasks | Object Detection, Semantic Segmentation |
| Published | 2017-09-02 |
| URL | http://arxiv.org/abs/1709.00516v1 |
| http://arxiv.org/pdf/1709.00516v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-filter-in-crf-based-semantic |
| Repo | |
| Framework | |
Q-Learning Algorithm for VoLTE Closed-Loop Power Control in Indoor Small Cells
| Title | Q-Learning Algorithm for VoLTE Closed-Loop Power Control in Indoor Small Cells |
| Authors | Faris B. Mismar, Brian L. Evans |
| Abstract | We propose a reinforcement learning (RL) based closed loop power control algorithm for the downlink of the voice over LTE (VoLTE) radio bearer for an indoor environment served by small cells. The main contributions of our paper are to 1) use RL to solve performance tuning problems in an indoor cellular network for voice bearers and 2) show that our derived lower bound loss in effective signal to interference plus noise ratio due to neighboring cell failure is sufficient for VoLTE power control purposes in practical cellular networks. In our simulation, the proposed RL-based power control algorithm significantly improves both voice retainability and mean opinion score compared to current industry standards. The improvement is due to maintaining an effective downlink signal to interference plus noise ratio against adverse network operational issues and faults. |
| Tasks | Q-Learning |
| Published | 2017-07-10 |
| URL | http://arxiv.org/abs/1707.03269v6 |
| http://arxiv.org/pdf/1707.03269v6.pdf | |
| PWC | https://paperswithcode.com/paper/q-learning-algorithm-for-volte-closed-loop |
| Repo | |
| Framework | |
Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks
| Title | Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks |
| Authors | Luca Caltagirone, Samuel Scheidegger, Lennart Svensson, Mattias Wahde |
| Abstract | In this work, a deep learning approach has been developed to carry out road detection using only LIDAR data. Starting from an unstructured point cloud, top-view images encoding several basic statistics such as mean elevation and density are generated. By considering a top-view representation, road detection is reduced to a single-scale problem that can be addressed with a simple and fast fully convolutional neural network (FCN). The FCN is specifically designed for the task of pixel-wise semantic segmentation by combining a large receptive field with high-resolution feature maps. The proposed system achieved excellent performance and it is among the top-performing algorithms on the KITTI road benchmark. Its fast inference makes it particularly suitable for real-time applications. |
| Tasks | Semantic Segmentation |
| Published | 2017-03-10 |
| URL | http://arxiv.org/abs/1703.03613v2 |
| http://arxiv.org/pdf/1703.03613v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-lidar-based-road-detection-using-fully |
| Repo | |
| Framework | |
Learning to segment on tiny datasets: a new shape model
| Title | Learning to segment on tiny datasets: a new shape model |
| Authors | Maxime Tremblay, André Zaccarin |
| Abstract | Current object segmentation algorithms are based on the hypothesis that one has access to a very large amount of data. In this paper, we aim to segment objects using only tiny datasets. To this extent, we propose a new automatic part-based object segmentation algorithm for non-deformable and semi-deformable objects in natural backgrounds. We have developed a novel shape descriptor which models the local boundaries of an object’s part. This shape descriptor is used in a bag-of-words approach for object detection. Once the detection process is performed, we use the background and foreground likelihood given by our trained shape model, and the information from the image content, to define a dense CRF model. We use a mean field approximation to solve it and thus segment the object of interest. Performance evaluated on different datasets shows that our approach can sometimes achieve results near state-of-the-art techniques based on big data while requiring only a tiny training set. |
| Tasks | Object Detection, Semantic Segmentation |
| Published | 2017-08-07 |
| URL | http://arxiv.org/abs/1708.02165v1 |
| http://arxiv.org/pdf/1708.02165v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-segment-on-tiny-datasets-a-new |
| Repo | |
| Framework | |
The game theoretic p-Laplacian and semi-supervised learning with few labels
| Title | The game theoretic p-Laplacian and semi-supervised learning with few labels |
| Authors | Jeff Calder |
| Abstract | We study the game theoretic p-Laplacian for semi-supervised learning on graphs, and show that it is well-posed in the limit of finite labeled data and infinite unlabeled data. In particular, we show that the continuum limit of graph-based semi-supervised learning with the game theoretic p-Laplacian is a weighted version of the continuous p-Laplace equation. We also prove that solutions to the graph p-Laplace equation are approximately Holder continuous with high probability. Our proof uses the viscosity solution machinery and the maximum principle on a graph. |
| Tasks | |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10144v4 |
| http://arxiv.org/pdf/1711.10144v4.pdf | |
| PWC | https://paperswithcode.com/paper/the-game-theoretic-p-laplacian-and-semi |
| Repo | |
| Framework | |
Off The Beaten Lane: AI Challenges In MOBAs Beyond Player Control
| Title | Off The Beaten Lane: AI Challenges In MOBAs Beyond Player Control |
| Authors | Michael Cook, Adam Summerville, Simon Colton |
| Abstract | MOBAs represent a huge segment of online gaming and are growing as both an eSport and a casual genre. The natural starting point for AI researchers interested in MOBAs is to develop an AI to play the game better than a human - but MOBAs have many more challenges besides adversarial AI. In this paper we introduce the reader to the wider context of MOBA culture, propose a range of challenges faced by the community today, and posit concrete AI projects that can be undertaken to begin solving them. |
| Tasks | |
| Published | 2017-06-09 |
| URL | http://arxiv.org/abs/1706.03122v1 |
| http://arxiv.org/pdf/1706.03122v1.pdf | |
| PWC | https://paperswithcode.com/paper/off-the-beaten-lane-ai-challenges-in-mobas |
| Repo | |
| Framework | |
Learning Uncertain Convolutional Features for Accurate Saliency Detection
| Title | Learning Uncertain Convolutional Features for Accurate Saliency Detection |
| Authors | Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, Baocai Yin |
| Abstract | Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate salient object detection. The key contribution of this work is to learn deep uncertain convolutional features (UCF), which encourage the robustness and accuracy of saliency detection. We achieve this via introducing a reformulated dropout (R-dropout) after specific convolutional layers to construct an uncertain ensemble of internal feature units. In addition, we propose an effective hybrid upsampling method to reduce the checkerboard artifacts of deconvolution operators in our decoder network. The proposed methods can also be applied to other deep convolutional networks. Compared with existing saliency detection methods, the proposed UCF model is able to incorporate uncertainties for more accurate object boundary inference. Extensive experiments demonstrate that our proposed saliency model performs favorably against state-of-the-art approaches. The uncertain feature learning mechanism as well as the upsampling method can significantly improve performance on other pixel-wise vision tasks. |
| Tasks | Object Detection, Saliency Detection, Salient Object Detection |
| Published | 2017-08-07 |
| URL | http://arxiv.org/abs/1708.02031v1 |
| http://arxiv.org/pdf/1708.02031v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-uncertain-convolutional-features-for |
| Repo | |
| Framework | |
Sum-Product-Quotient Networks
| Title | Sum-Product-Quotient Networks |
| Authors | Or Sharir, Amnon Shashua |
| Abstract | We present a novel tractable generative model that extends Sum-Product Networks (SPNs) and significantly boosts their power. We call it Sum-Product-Quotient Networks (SPQNs), whose core concept is to incorporate conditional distributions into the model by direct computation using quotient nodes, e.g. $P(AB) = \frac{P(A,B)}{P(B)}$. We provide sufficient conditions for the tractability of SPQNs that generalize and relax the decomposable and complete tractability conditions of SPNs. These relaxed conditions give rise to an exponential boost to the expressive efficiency of our model, i.e. we prove that there are distributions which SPQNs can compute efficiently but require SPNs to be of exponential size. Thus, we narrow the gap in expressivity between tractable graphical models and other Neural Network-based generative models. |
| Tasks | |
| Published | 2017-10-12 |
| URL | http://arxiv.org/abs/1710.04404v3 |
| http://arxiv.org/pdf/1710.04404v3.pdf | |
| PWC | https://paperswithcode.com/paper/sum-product-quotient-networks |
| Repo | |
| Framework | |
Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization
| Title | Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization |
| Authors | Luis Muñoz-González, Battista Biggio, Ambra Demontis, Andrea Paudice, Vasin Wongrassamee, Emil C. Lupu, Fabio Roli |
| Abstract | A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction of the training data is controlled by the attacker and manipulated to subvert the learning process. To date, these attacks have been devised only against a limited class of binary learning algorithms, due to the inherent complexity of the gradient-based procedure used to optimize the poisoning points (a.k.a. adversarial training examples). In this work, we rst extend the de nition of poisoning attacks to multiclass problems. We then propose a novel poisoning algorithm based on the idea of back-gradient optimization, i.e., to compute the gradient of interest through automatic di erentiation, while also reversing the learning procedure to drastically reduce the attack complexity. Compared to current poisoning strategies, our approach is able to target a wider class of learning algorithms, trained with gradient- based procedures, including neural networks and deep learning architectures. We empirically evaluate its e ectiveness on several application examples, including spam ltering, malware detection, and handwritten digit recognition. We nally show that, similarly to adversarial test examples, adversarial training examples can also be transferred across di erent learning algorithms. |
| Tasks | data poisoning, Handwritten Digit Recognition, Malware Detection |
| Published | 2017-08-29 |
| URL | http://arxiv.org/abs/1708.08689v1 |
| http://arxiv.org/pdf/1708.08689v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-poisoning-of-deep-learning-algorithms |
| Repo | |
| Framework | |
Statistical inference using SGD
| Title | Statistical inference using SGD |
| Authors | Tianyang Li, Liu Liu, Anastasios Kyrillidis, Constantine Caramanis |
| Abstract | We present a novel method for frequentist statistical inference in $M$-estimation problems, based on stochastic gradient descent (SGD) with a fixed step size: we demonstrate that the average of such SGD sequences can be used for statistical inference, after proper scaling. An intuitive analysis using the Ornstein-Uhlenbeck process suggests that such averages are asymptotically normal. From a practical perspective, our SGD-based inference procedure is a first order method, and is well-suited for large scale problems. To show its merits, we apply it to both synthetic and real datasets, and demonstrate that its accuracy is comparable to classical statistical methods, while requiring potentially far less computation. |
| Tasks | |
| Published | 2017-05-21 |
| URL | http://arxiv.org/abs/1705.07477v2 |
| http://arxiv.org/pdf/1705.07477v2.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-inference-using-sgd |
| Repo | |
| Framework | |
Tensor Regression Networks
| Title | Tensor Regression Networks |
| Authors | Jean Kossaifi, Zachary C. Lipton, Aran Khanna, Tommaso Furlanello, Anima Anandkumar |
| Abstract | Convolutional neural networks typically consist of many convolutional layers followed by several fully-connected layers. While convolutional layers map between high-order activation tensors, the fully-connected layers operate on flattened activation vectors. Despite its success, this approach has notable drawbacks. Flattening discards multilinear structure in the activations, and fully-connected layers require many parameters. We address these problems by incorporating tensor algebraic operations that preserve multilinear structure at every layer. First, we introduce Tensor Contraction Layers (TCLs) that reduce the dimensionality of their input while preserving their multilinear structure using tensor contraction. Next, we introduce Tensor Regression Layers (TRLs), to express outputs through a low-rank multilinear mapping from a high-order activation tensor to an output tensor of arbitrary order. We learn the contraction and regression factors end-to-end, and by imposing low rank on both, we produce accurate nets with few parameters. Additionally, our layers regularize networks by imposing low-rank constraints on the activations (TCL) and regression weights (TRL). Experiments on ImageNet show that, applied to VGG and ResNet architectures, TCLs and TRLs reduce the number of parameters compared to fully-connected layers by more than 65% without impacting accuracy. |
| Tasks | |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08308v3 |
| http://arxiv.org/pdf/1707.08308v3.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-regression-networks |
| Repo | |
| Framework | |
Multipartite Pooling for Deep Convolutional Neural Networks
| Title | Multipartite Pooling for Deep Convolutional Neural Networks |
| Authors | Arash Shahriari, Fatih Porikli |
| Abstract | We propose a novel pooling strategy that learns how to adaptively rank deep convolutional features for selecting more informative representations. To this end, we exploit discriminative analysis to project the features onto a space spanned by the number of classes in the dataset under study. This maps the notion of labels in the feature space into instances in the projected space. We employ these projected distances as a measure to rank the existing features with respect to their specific discriminant power for each individual class. We then apply multipartite ranking to score the separability of the instances and aggregate one-versus-all scores to compute an overall distinction score for each feature. For the pooling, we pick features with the highest scores in a pooling window instead of maximum, average or stochastic random assignments. Our experiments on various benchmarks confirm that the proposed strategy of multipartite pooling is highly beneficial to consistently improve the performance of deep convolutional networks via better generalization of the trained models for the test-time data. |
| Tasks | |
| Published | 2017-10-20 |
| URL | http://arxiv.org/abs/1710.07435v1 |
| http://arxiv.org/pdf/1710.07435v1.pdf | |
| PWC | https://paperswithcode.com/paper/multipartite-pooling-for-deep-convolutional |
| Repo | |
| Framework | |
User-centric Composable Services: A New Generation of Personal Data Analytics
| Title | User-centric Composable Services: A New Generation of Personal Data Analytics |
| Authors | Jianxin Zhao, Richard Mortier, Jon Crowcroft, Liang Wang |
| Abstract | Machine Learning (ML) techniques, such as Neural Network, are widely used in today’s applications. However, there is still a big gap between the current ML systems and users’ requirements. ML systems focus on improving the performance of models in training, while individual users cares more about response time and expressiveness of the tool. Many existing research and product begin to move computation towards edge devices. Based on the numerical computing system Owl, we propose to build the Zoo system to support construction, compose, and deployment of ML models on edge and local devices. |
| Tasks | |
| Published | 2017-10-25 |
| URL | http://arxiv.org/abs/1710.09027v3 |
| http://arxiv.org/pdf/1710.09027v3.pdf | |
| PWC | https://paperswithcode.com/paper/user-centric-composable-services-a-new |
| Repo | |
| Framework | |
