Paper Group ANR 251
Modelling curvature of a bent paper leaf. Generating High-Resolution Fashion Model Images Wearing Custom Outfits. Active Learning for Network Intrusion Detection. VFNet: A Convolutional Architecture for Accent Classification. GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding. On Network Embedding for Machine Learn …
Modelling curvature of a bent paper leaf
| Title | Modelling curvature of a bent paper leaf |
| Authors | Sasikanth Raghava Goteti |
| Abstract | In this article, we briefly describe various tools and approaches that algebraic geometry has to offer to straighten bent objects. Throughout this article we will consider a specific example of a bent or curved piece of paper which in our case acts very much like an elastica curve. We conclude this article with a suggestion to algebraic geometry as a viable and fast performance alternative of neural networks in vision and machine learning. The purpose of this article is not to build a full blown framework but to show possibility of using algebraic geometry as an alternative to neural networks for recognizing or extracting features on manifolds. |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04898v1 |
| https://arxiv.org/pdf/1912.04898v1.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-curvature-of-a-bent-paper-leaf |
| Repo | |
| Framework | |
Generating High-Resolution Fashion Model Images Wearing Custom Outfits
| Title | Generating High-Resolution Fashion Model Images Wearing Custom Outfits |
| Authors | Gökhan Yildirim, Nikolay Jetchev, Roland Vollgraf, Urs Bergmann |
| Abstract | Visualizing an outfit is an essential part of shopping for clothes. Due to the combinatorial aspect of combining fashion articles, the available images are limited to a pre-determined set of outfits. In this paper, we broaden these visualizations by generating high-resolution images of fashion models wearing a custom outfit under an input body pose. We show that our approach can not only transfer the style and the pose of one generated outfit to another, but also create realistic images of human bodies and garments. |
| Tasks | |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08847v1 |
| https://arxiv.org/pdf/1908.08847v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-high-resolution-fashion-model |
| Repo | |
| Framework | |
Active Learning for Network Intrusion Detection
| Title | Active Learning for Network Intrusion Detection |
| Authors | Amir Ziai |
| Abstract | Network operators are generally aware of common attack vectors that they defend against. For most networks the vast majority of traffic is legitimate. However new attack vectors are continually designed and attempted by bad actors which bypass detection and go unnoticed due to low volume. One strategy for finding such activity is to look for anomalous behavior. Investigating anomalous behavior requires significant time and resources. Collecting a large number of labeled examples for training supervised models is both prohibitively expensive and subject to obsoletion as new attacks surface. A purely unsupervised methodology is ideal; however, research has shown that even a very small number of labeled examples can significantly improve the quality of anomaly detection. A methodology that minimizes the number of required labels while maximizing the quality of detection is desirable. False positives in this context result in wasted effort or blockage of legitimate traffic and false negatives translate to undetected attacks. We propose a general active learning framework and experiment with different choices of learners and sampling strategies. |
| Tasks | Active Learning, Anomaly Detection, Intrusion Detection, Network Intrusion Detection |
| Published | 2019-04-02 |
| URL | http://arxiv.org/abs/1904.01555v1 |
| http://arxiv.org/pdf/1904.01555v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-for-network-intrusion |
| Repo | |
| Framework | |
VFNet: A Convolutional Architecture for Accent Classification
| Title | VFNet: A Convolutional Architecture for Accent Classification |
| Authors | Asad Ahmed, Pratham Tangri, Anirban Panda, Dhruv Ramani, Samarjit Karmakar |
| Abstract | Understanding accent is an issue which can derail any human-machine interaction. Accent classification makes this task easier by identifying the accent being spoken by a person so that the correct words being spoken can be identified by further processing, since same noises can mean entirely different words in different accents of the same language. In this paper, we present VFNet (Variable Filter Net), a convolutional neural network (CNN) based architecture which captures a hierarchy of features to beat the previous benchmarks of accent classification, through a novel and elegant technique of applying variable filter sizes along the frequency band of the audio utterances. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06697v1 |
| https://arxiv.org/pdf/1910.06697v1.pdf | |
| PWC | https://paperswithcode.com/paper/vfnet-a-convolutional-architecture-for-accent |
| Repo | |
| Framework | |
GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding
| Title | GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding |
| Authors | Chenhui Deng, Zhiqiang Zhao, Yongyu Wang, Zhiru Zhang, Zhuo Feng |
| Abstract | Graph embedding techniques have been increasingly deployed in a multitude of different applications that involve learning on non-Euclidean data. However, existing graph embedding models either fail to incorporate node attribute information during training or suffer from node attribute noise, which compromises the accuracy. Moreover, very few of them scale to large graphs due to their high computational complexity and memory usage. In this paper we propose GraphZoom, a multi-level framework for improving both accuracy and scalability of unsupervised graph embedding algorithms. GraphZoom first performs graph fusion to generate a new graph that effectively encodes the topology of the original graph and the node attribute information. This fused graph is then repeatedly coarsened into much smaller graphs by merging nodes with high spectral similarities. GraphZoom allows any existing embedding methods to be applied to the coarsened graph, before it progressively refine the embeddings obtained at the coarsest level to increasingly finer graphs. We have evaluated our approach on a number of popular graph datasets for both transductive and inductive tasks. Our experiments show that GraphZoom can substantially increase the classification accuracy and significantly accelerate the entire graph embedding process by up to 40.8x, when compared to the state-of-the-art unsupervised embedding methods. |
| Tasks | Graph Embedding |
| Published | 2019-10-06 |
| URL | https://arxiv.org/abs/1910.02370v2 |
| https://arxiv.org/pdf/1910.02370v2.pdf | |
| PWC | https://paperswithcode.com/paper/graphzoom-a-multi-level-spectral-approach-for |
| Repo | |
| Framework | |
On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network
| Title | On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network |
| Authors | Tobias Skovgaard Jepsen, Christian S. Jensen, Thomas Dyhre Nielsen |
| Abstract | Road networks are a type of spatial network, where edges may be associated with qualitative information such as road type and speed limit. Unfortunately, such information is often incomplete; for instance, OpenStreetMap only has speed limits for 13% of all Danish road segments. This is problematic for analysis tasks that rely on such information for machine learning. To enable machine learning in such circumstances, one may consider the application of network embedding methods to extract structural information from the network. However, these methods have so far mostly been used in the context of social networks, which differ significantly from road networks in terms of, e.g., node degree and level of homophily (which are key to the performance of many network embedding methods). We analyze the use of network embedding methods, specifically node2vec, for learning road segment embeddings in road networks. Due to the often limited availability of information on other relevant road characteristics, the analysis focuses on leveraging the spatial network structure. Our results suggest that network embedding methods can indeed be used for deriving relevant network features (that may, e.g, be used for predicting speed limits), but that the qualities of the embeddings differ from embeddings for social networks. |
| Tasks | Network Embedding |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06217v2 |
| https://arxiv.org/pdf/1911.06217v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-network-embedding-for-machine-learning-on |
| Repo | |
| Framework | |
Comparison of Possibilistic Fuzzy Local Information C-Means and Possibilistic K-Nearest Neighbors for Synthetic Aperture Sonar Image Segmentation
| Title | Comparison of Possibilistic Fuzzy Local Information C-Means and Possibilistic K-Nearest Neighbors for Synthetic Aperture Sonar Image Segmentation |
| Authors | Joshua Peeples, Matthew Cook, Daniel Suen, Alina Zare, James Keller |
| Abstract | Synthetic aperture sonar (SAS) imagery can generate high resolution images of the seafloor. Thus, segmentation algorithms can be used to partition the images into different seafloor environments. In this paper, we compare two possibilistic segmentation approaches. Possibilistic approaches allow for the ability to detect novel or outlier environments as well as well known classes. The Possibilistic Fuzzy Local Information C-Means (PFLICM) algorithm has been previously applied to segment SAS imagery. Additionally, the Possibilistic K-Nearest Neighbors (PKNN) algorithm has been used in other domains such as landmine detection and hyperspectral imagery. In this paper, we compare the segmentation performance of a semi-supervised approach using PFLICM and a supervised method using Possibilistic K-NN. We include final segmentation results on multiple SAS images and a quantitative assessment of each algorithm. |
| Tasks | Semantic Segmentation |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.01014v1 |
| http://arxiv.org/pdf/1904.01014v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-possibilistic-fuzzy-local |
| Repo | |
| Framework | |
Regret Analysis of Causal Bandit Problems
| Title | Regret Analysis of Causal Bandit Problems |
| Authors | Yangyi Lu, Amirhossein Meisami, Ambuj Tewari, Zhenyu Yan |
| Abstract | We study how to learn optimal interventions sequentially given causal information represented as a causal graph along with associated conditional distributions. Causal modeling is useful in real world problems like online advertisement where complex causal mechanisms underlie the relationship between interventions and outcomes. We propose two algorithms, causal upper confidence bound (C-UCB) and causal Thompson Sampling (C-TS), that enjoy improved cumulative regret bounds compared with algorithms that do not use causal information. We thus resolve an open problem posed by \cite{lattimore2016causal}. Further, we extend C-UCB and C-TS to the linear bandit setting and propose causal linear UCB (CL-UCB) and causal linear TS (CL-TS) algorithms. These algorithms enjoy a cumulative regret bound that only scales with the feature dimension. Our experiments show the benefit of using causal information. For example, we observe that even with a few hundreds of iterations, the regret of causal algorithms is less than that of standard algorithms by a factor of three. We also show that under certain causal structures, our algorithms scale better than the standard bandit algorithms as the number of interventions increases. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04938v2 |
| https://arxiv.org/pdf/1910.04938v2.pdf | |
| PWC | https://paperswithcode.com/paper/regret-analysis-of-causal-bandit-problems |
| Repo | |
| Framework | |
Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network
| Title | Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network |
| Authors | Sheng Wan, Chen Gong, Ping Zhong, Shirui Pan, Guangyu Li, Jian Yang |
| Abstract | In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed Graph Convolutional Network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2D image grids. Second, we refine the graph edge weight and the connective relationships among image regions by learning the improved adjacency matrix and the ‘edge filter’, so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in accurate region representations, and vice versa. The experiments carried out on three real-world benchmark datasets demonstrate that the proposed method yields significant improvement in the classification performance when compared with some state-of-the-art approaches. |
| Tasks | Hyperspectral Image Classification, Image Classification |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.11953v1 |
| https://arxiv.org/pdf/1909.11953v1.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-image-classification-with-2 |
| Repo | |
| Framework | |
Rallying Adversarial Techniques against Deep Learning for Network Security
| Title | Rallying Adversarial Techniques against Deep Learning for Network Security |
| Authors | Joseph Clements, Yuzhe Yang, Ankur Sharma, Hongxin Hu, Yingjie Lao |
| Abstract | Recent advances in artificial intelligence and the increasing need for powerful defensive measures in the domain of network security, have led to the adoption of deep learning approaches for use in network intrusion detection systems. These methods have achieved superior performance against conventional network attacks, which enable the deployment of practical security systems to unique and dynamic sectors. Adversarial machine learning, unfortunately, has recently shown that deep learning models are inherently vulnerable to adversarial modifications on their input data. Because of this susceptibility, the deep learning models deployed to power a network defense could in fact be the weakest entry point for compromising a network system. In this paper, we show that by modifying on average as little as 1.38 of the input features, an adversary can generate malicious inputs which effectively fool a deep learning based NIDS. Therefore, when designing such systems, it is crucial to consider the performance from not only the conventional network security perspective but also the adversarial machine learning domain. |
| Tasks | Intrusion Detection, Network Intrusion Detection |
| Published | 2019-03-27 |
| URL | http://arxiv.org/abs/1903.11688v1 |
| http://arxiv.org/pdf/1903.11688v1.pdf | |
| PWC | https://paperswithcode.com/paper/rallying-adversarial-techniques-against-deep |
| Repo | |
| Framework | |
Learning Task Knowledge and its Scope of Applicability in Experience-Based Planning Domains
| Title | Learning Task Knowledge and its Scope of Applicability in Experience-Based Planning Domains |
| Authors | Vahid Mokhtari, Luis Seabra Lopes, Armando Pinho, Roman Manevich |
| Abstract | Experience-based planning domains (EBPDs) have been recently proposed to improve problem solving by learning from experience. EBPDs provide important concepts for long-term learning and planning in robotics. They rely on acquiring and using task knowledge, i.e., activity schemata, for generating concrete solutions to problem instances in a class of tasks. Using Three-Valued Logic Analysis (TVLA), we extend previous work to generate a set of conditions as the scope of applicability for an activity schema. The inferred scope is a bounded representation of a set of problems of potentially unbounded size, in the form of a 3-valued logical structure, which allows an EBPD system to automatically find an applicable activity schema for solving task problems. We demonstrate the utility of our approach in a set of classes of problems in a simulated domain and a class of real world tasks in a fully physically simulated PR2 robot in Gazebo. |
| Tasks | |
| Published | 2019-02-27 |
| URL | http://arxiv.org/abs/1902.10770v2 |
| http://arxiv.org/pdf/1902.10770v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-task-knowledge-and-its-scope-of |
| Repo | |
| Framework | |
Convolutional Sparse Coding for Compressed Sensing CT Reconstruction
| Title | Convolutional Sparse Coding for Compressed Sensing CT Reconstruction |
| Authors | Peng Bao, Wenjun Xia, Kang Yang, Weiyan Chen, Mianyi Chen, Yan Xi, Shanzhou Niu, Jiliu Zhou, He Zhang, Huaiqiang Sun, Zhangyang Wang, Yi Zhang |
| Abstract | Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore the consistency of pixels in overlapped patches. In addition, the features learned by these methods always contain shifted versions of the same features. In recent years, convolutional sparse coding (CSC) has been developed to address these problems. In this paper, inspired by several successful applications of CSC in the field of signal processing, we explore the potential of CSC in sparse-view CT reconstruction. By directly working on the whole image, without the necessity of dividing the image into overlapped patches in DL-based methods, the proposed methods can maintain more details and avoid artifacts caused by patch aggregation. With predetermined filters, an alternating scheme is developed to optimize the objective function. Extensive experiments with simulated and real CT data were performed to validate the effectiveness of the proposed methods. Qualitative and quantitative results demonstrate that the proposed methods achieve better performance than several existing state-of-the-art methods. |
| Tasks | Computed Tomography (CT), Dictionary Learning, Image Reconstruction |
| Published | 2019-03-20 |
| URL | http://arxiv.org/abs/1903.08549v1 |
| http://arxiv.org/pdf/1903.08549v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-sparse-coding-for-compressed |
| Repo | |
| Framework | |
SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks
| Title | SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks |
| Authors | Tuo Feng, Dongbing Gu |
| Abstract | Recently end-to-end unsupervised deep learning methods have achieved an effect beyond geometric methods for visual depth and ego-motion estimation tasks. These data-based learning methods perform more robustly and accurately in some of the challenging scenes. The encoder-decoder network has been widely used in the depth estimation and the RCNN has brought significant improvements in the ego-motion estimation. Furthermore, the latest use of Generative Adversarial Nets(GANs) in depth and ego-motion estimation has demonstrated that the estimation could be further improved by generating pictures in the game learning process. This paper proposes a novel unsupervised network system for visual depth and ego-motion estimation: Stacked Generative Adversarial Network(SGANVO). It consists of a stack of GAN layers, of which the lowest layer estimates the depth and ego-motion while the higher layers estimate the spatial features. It can also capture the temporal dynamic due to the use of a recurrent representation across the layers. See Fig.1 for details. We select the most commonly used KITTI [1] data set for evaluation. The evaluation results show that our proposed method can produce better or comparable results in depth and ego-motion estimation. |
| Tasks | Depth Estimation, Motion Estimation, Visual Odometry |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.08889v1 |
| https://arxiv.org/pdf/1906.08889v1.pdf | |
| PWC | https://paperswithcode.com/paper/sganvo-unsupervised-deep-visual-odometry-and |
| Repo | |
| Framework | |
One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods
| Title | One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods |
| Authors | Filip Hanzely, Peter Richtárik |
| Abstract | We propose a remarkably general variance-reduced method suitable for solving regularized empirical risk minimization problems with either a large number of training examples, or a large model dimension, or both. In special cases, our method reduces to several known and previously thought to be unrelated methods, such as {\tt SAGA}, {\tt LSVRG}, {\tt JacSketch}, {\tt SEGA} and {\tt ISEGA}, and their arbitrary sampling and proximal generalizations. However, we also highlight a large number of new specific algorithms with interesting properties. We provide a single theorem establishing linear convergence of the method under smoothness and quasi strong convexity assumptions. With this theorem we recover best-known and sometimes improved rates for known methods arising in special cases. As a by-product, we provide the first unified method and theory for stochastic gradient and stochastic coordinate descent type methods. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11266v2 |
| https://arxiv.org/pdf/1905.11266v2.pdf | |
| PWC | https://paperswithcode.com/paper/one-method-to-rule-them-all-variance |
| Repo | |
| Framework | |
RPM-Oriented Query Rewriting Framework for E-commerce Keyword-Based Sponsored Search
| Title | RPM-Oriented Query Rewriting Framework for E-commerce Keyword-Based Sponsored Search |
| Authors | Xiuying Chen, Daorui Xiao, Shen Gao, Guojun Liu, Wei Lin, Bo Zheng, Dongyan Zhao, Rui Yan |
| Abstract | Sponsored search optimizes revenue and relevance, which is estimated by Revenue Per Mille (RPM). Existing sponsored search models are all based on traditional statistical models, which have poor RPM performance when queries follow a heavy-tailed distribution. Here, we propose an RPM-oriented Query Rewriting Framework (RQRF) which outputs related bid keywords that can yield high RPM. RQRF embeds both queries and bid keywords to vectors in the same implicit space, converting the rewriting probability between each query and keyword to the distance between the two vectors. For label construction, we propose an RPM-oriented sample construction method, labeling keywords based on whether or not they can lead to high RPM. Extensive experiments are conducted to evaluate performance of RQRF. In a one month large-scale real-world traffic of e-commerce sponsored search system, the proposed model significantly outperforms traditional baseline. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12527v2 |
| https://arxiv.org/pdf/1910.12527v2.pdf | |
| PWC | https://paperswithcode.com/paper/rpm-oriented-query-rewriting-framework-for-e |
| Repo | |
| Framework | |
