Paper Group ANR 560
New efficient algorithms for multiple change-point detection with kernels. Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines. On (Commercial) Benefits of Automatic Text Summarization Systems in the News Domain: A Case of Media Monitoring and Media Response Analysis. Traffic Sign Timely Vis …
New efficient algorithms for multiple change-point detection with kernels
| Title | New efficient algorithms for multiple change-point detection with kernels |
| Authors | Alain Celisse, Guillemette Marot, Morgane Pierre-Jean, Guillem Rigaill |
| Abstract | Several statistical approaches based on reproducing kernels have been proposed to detect abrupt changes arising in the full distribution of the observations and not only in the mean or variance. Some of these approaches enjoy good statistical properties (oracle inequality, \ldots). Nonetheless, they have a high computational cost both in terms of time and memory. This makes their application difficult even for small and medium sample sizes ($n< 10^4$). This computational issue is addressed by first describing a new efficient and exact algorithm for kernel multiple change-point detection with an improved worst-case complexity that is quadratic in time and linear in space. It allows dealing with medium size signals (up to $n \approx 10^5$). Second, a faster but approximation algorithm is described. It is based on a low-rank approximation to the Gram matrix. It is linear in time and space. This approximation algorithm can be applied to large-scale signals ($n \geq 10^6$). These exact and approximation algorithms have been implemented in \texttt{R} and \texttt{C} for various kernels. The computational and statistical performances of these new algorithms have been assessed through empirical experiments. The runtime of the new algorithms is observed to be faster than that of other considered procedures. Finally, simulations confirmed the higher statistical accuracy of kernel-based approaches to detect changes that are not only in the mean. These simulations also illustrate the flexibility of kernel-based approaches to analyze complex biological profiles made of DNA copy number and allele B frequencies. An R package implementing the approach will be made available on github. |
| Tasks | Change Point Detection |
| Published | 2017-10-12 |
| URL | http://arxiv.org/abs/1710.04556v1 |
| http://arxiv.org/pdf/1710.04556v1.pdf | |
| PWC | https://paperswithcode.com/paper/new-efficient-algorithms-for-multiple-change |
| Repo | |
| Framework | |
Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines
| Title | Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines |
| Authors | Philip S. Thomas, Emma Brunskill |
| Abstract | We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000). |
| Tasks | Policy Gradient Methods |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06643v1 |
| http://arxiv.org/pdf/1706.06643v1.pdf | |
| PWC | https://paperswithcode.com/paper/policy-gradient-methods-for-reinforcement |
| Repo | |
| Framework | |
On (Commercial) Benefits of Automatic Text Summarization Systems in the News Domain: A Case of Media Monitoring and Media Response Analysis
| Title | On (Commercial) Benefits of Automatic Text Summarization Systems in the News Domain: A Case of Media Monitoring and Media Response Analysis |
| Authors | Pashutan Modaresi, Philipp Gross, Siavash Sefidrodi, Mirja Eckhof, Stefan Conrad |
| Abstract | In this work, we present the results of a systematic study to investigate the (commercial) benefits of automatic text summarization systems in a real world scenario. More specifically, we define a use case in the context of media monitoring and media response analysis and claim that even using a simple query-based extractive approach can dramatically save the processing time of the employees without significantly reducing the quality of their work. |
| Tasks | Text Summarization |
| Published | 2017-01-03 |
| URL | http://arxiv.org/abs/1701.00728v1 |
| http://arxiv.org/pdf/1701.00728v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-commercial-benefits-of-automatic-text |
| Repo | |
| Framework | |
Traffic Sign Timely Visual Recognizability Evaluation Based on 3D Measurable Point Clouds
| Title | Traffic Sign Timely Visual Recognizability Evaluation Based on 3D Measurable Point Clouds |
| Authors | Shanxin Zhang, Cheng Wang, Zhuang Yang, Chenglu Wen, Jonathan Li, Chenhui Yang |
| Abstract | The timely provision of traffic sign information to drivers is essential for the drivers to respond, to ensure safe driving, and to avoid traffic accidents in a timely manner. We proposed a timely visual recognizability quantitative evaluation method for traffic signs in large-scale transportation environments. To achieve this goal, we first address the concept of a visibility field to reflect the visible distribution of three-dimensional (3D) space and construct a traffic sign Visibility Evaluation Model (VEM) to measure the traffic sign visibility for a given viewpoint. Then, based on the VEM, we proposed the concept of the Visual Recognizability Field (VRF) to reflect the visual recognizability distribution in 3D space and established a Visual Recognizability Evaluation Model (VREM) to measure a traffic sign visual recognizability for a given viewpoint. Next, we proposed a Traffic Sign Timely Visual Recognizability Evaluation Model (TSTVREM) by combining VREM, the actual maximum continuous visual recognizable distance, and traffic big data to measure a traffic sign visual recognizability in different lanes. Finally, we presented an automatic algorithm to implement the TSTVREM model through traffic sign and road marking detection and classification, traffic sign environment point cloud segmentation, viewpoints calculation, and TSTVREM model realization. The performance of our method for traffic sign timely visual recognizability evaluation is tested on three road point clouds acquired by a mobile laser scanning system (RIEGL VMX-450) according to Road Traffic Signs and Markings (GB 5768-1999 in China), showing that our method is feasible and efficient. |
| Tasks | |
| Published | 2017-10-10 |
| URL | http://arxiv.org/abs/1710.03553v1 |
| http://arxiv.org/pdf/1710.03553v1.pdf | |
| PWC | https://paperswithcode.com/paper/traffic-sign-timely-visual-recognizability |
| Repo | |
| Framework | |
Regularization, sparse recovery, and median-of-means tournaments
| Title | Regularization, sparse recovery, and median-of-means tournaments |
| Authors | Gábor Lugosi, Shahar Mendelson |
| Abstract | A regularized risk minimization procedure for regression function estimation is introduced that achieves near optimal accuracy and confidence under general conditions, including heavy-tailed predictor and response variables. The procedure is based on median-of-means tournaments, introduced by the authors in [8]. It is shown that the new procedure outperforms standard regularized empirical risk minimization procedures such as lasso or slope in heavy-tailed problems. |
| Tasks | |
| Published | 2017-01-15 |
| URL | http://arxiv.org/abs/1701.04112v2 |
| http://arxiv.org/pdf/1701.04112v2.pdf | |
| PWC | https://paperswithcode.com/paper/regularization-sparse-recovery-and-median-of |
| Repo | |
| Framework | |
Isotropic reconstruction of 3D fluorescence microscopy images using convolutional neural networks
| Title | Isotropic reconstruction of 3D fluorescence microscopy images using convolutional neural networks |
| Authors | Martin Weigert, Loic Royer, Florian Jug, Gene Myers |
| Abstract | Fluorescence microscopy images usually show severe anisotropy in axial versus lateral resolution. This hampers downstream processing, i.e. the automatic extraction of quantitative biological data. While deconvolution methods and other techniques to address this problem exist, they are either time consuming to apply or limited in their ability to remove anisotropy. We propose a method to recover isotropic resolution from readily acquired anisotropic data. We achieve this using a convolutional neural network that is trained end-to-end from the same anisotropic body of data we later apply the network to. The network effectively learns to restore the full isotropic resolution by restoring the image under a trained, sample specific image prior. We apply our method to $3$ synthetic and $3$ real datasets and show that our results improve on results from deconvolution and state-of-the-art super-resolution techniques. Finally, we demonstrate that a standard 3D segmentation pipeline performs on the output of our network with comparable accuracy as on the full isotropic data. |
| Tasks | Super-Resolution |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01510v1 |
| http://arxiv.org/pdf/1704.01510v1.pdf | |
| PWC | https://paperswithcode.com/paper/isotropic-reconstruction-of-3d-fluorescence |
| Repo | |
| Framework | |
Bayesian Active Edge Evaluation on Expensive Graphs
| Title | Bayesian Active Edge Evaluation on Expensive Graphs |
| Authors | Sanjiban Choudhury, Siddhartha Srinivasa, Sebastian Scherer |
| Abstract | Robots operate in environments with varying implicit structure. For instance, a helicopter flying over terrain encounters a very different arrangement of obstacles than a robotic arm manipulating objects on a cluttered table top. State-of-the-art motion planning systems do not exploit this structure, thereby expending valuable planning effort searching for implausible solutions. We are interested in planning algorithms that actively infer the underlying structure of the valid configuration space during planning in order to find solutions with minimal effort. Consider the problem of evaluating edges on a graph to quickly discover collision-free paths. Evaluating edges is expensive, both for robots with complex geometries like robot arms, and for robots with limited onboard computation like UAVs. Until now, this challenge has been addressed via laziness i.e. deferring edge evaluation until absolutely necessary, with the hope that edges turn out to be valid. However, all edges are not alike in value - some have a lot of potentially good paths flowing through them, and some others encode the likelihood of neighbouring edges being valid. This leads to our key insight - instead of passive laziness, we can actively choose edges that reduce the uncertainty about the validity of paths. We show that this is equivalent to the Bayesian active learning paradigm of decision region determination (DRD). However, the DRD problem is not only combinatorially hard, but also requires explicit enumeration of all possible worlds. We propose a novel framework that combines two DRD algorithms, DIRECT and BISECT, to overcome both issues. We show that our approach outperforms several state-of-the-art algorithms on a spectrum of planning problems for mobile robots, manipulators and autonomous helicopters. |
| Tasks | Active Learning, Motion Planning |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07329v1 |
| http://arxiv.org/pdf/1711.07329v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-active-edge-evaluation-on-expensive |
| Repo | |
| Framework | |
Skip Connections Eliminate Singularities
| Title | Skip Connections Eliminate Singularities |
| Authors | A. Emin Orhan, Xaq Pitkow |
| Abstract | Skip connections made the training of very deep networks possible and have become an indispensable component in a variety of neural architectures. A completely satisfactory explanation for their success remains elusive. Here, we present a novel explanation for the benefits of skip connections in training very deep networks. The difficulty of training deep networks is partly due to the singularities caused by the non-identifiability of the model. Several such singularities have been identified in previous works: (i) overlap singularities caused by the permutation symmetry of nodes in a given layer, (ii) elimination singularities corresponding to the elimination, i.e. consistent deactivation, of nodes, (iii) singularities generated by the linear dependence of the nodes. These singularities cause degenerate manifolds in the loss landscape that slow down learning. We argue that skip connections eliminate these singularities by breaking the permutation symmetry of nodes, by reducing the possibility of node elimination and by making the nodes less linearly dependent. Moreover, for typical initializations, skip connections move the network away from the “ghosts” of these singularities and sculpt the landscape around them to alleviate the learning slow-down. These hypotheses are supported by evidence from simplified models, as well as from experiments with deep networks trained on real-world datasets. |
| Tasks | |
| Published | 2017-01-31 |
| URL | http://arxiv.org/abs/1701.09175v8 |
| http://arxiv.org/pdf/1701.09175v8.pdf | |
| PWC | https://paperswithcode.com/paper/skip-connections-eliminate-singularities |
| Repo | |
| Framework | |
Language-depedent I-Vectors for LRE15
| Title | Language-depedent I-Vectors for LRE15 |
| Authors | Niko Brümmer, Albert Swart |
| Abstract | A standard recipe for spoken language recognition is to apply a Gaussian back-end to i-vectors. This ignores the uncertainty in the i-vector extraction, which could be important especially for short utterances. A recent paper by Cumani, Plchot and Fer proposes a solution to propagate that uncertainty into the backend. We propose an alternative method of propagating the uncertainty. |
| Tasks | |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1710.00085v1 |
| http://arxiv.org/pdf/1710.00085v1.pdf | |
| PWC | https://paperswithcode.com/paper/language-depedent-i-vectors-for-lre15 |
| Repo | |
| Framework | |
Identifying Restaurant Features via Sentiment Analysis on Yelp Reviews
| Title | Identifying Restaurant Features via Sentiment Analysis on Yelp Reviews |
| Authors | Boya Yu, Jiaxu Zhou, Yi Zhang, Yunong Cao |
| Abstract | Many people use Yelp to find a good restaurant. Nonetheless, with only an overall rating for each restaurant, Yelp offers not enough information for independently judging its various aspects such as environment, service or flavor. In this paper, we introduced a machine learning based method to characterize such aspects for particular types of restaurants. The main approach used in this paper is to use a support vector machine (SVM) model to decipher the sentiment tendency of each review from word frequency. Word scores generated from the SVM models are further processed into a polarity index indicating the significance of each word for special types of restaurant. Customers overall tend to express more sentiment regarding service. As for the distinction between different cuisines, results that match the common sense are obtained: Japanese cuisines are usually fresh, some French cuisines are overpriced while Italian Restaurants are often famous for their pizzas. |
| Tasks | Common Sense Reasoning, Sentiment Analysis |
| Published | 2017-09-20 |
| URL | http://arxiv.org/abs/1709.08698v1 |
| http://arxiv.org/pdf/1709.08698v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-restaurant-features-via-sentiment |
| Repo | |
| Framework | |
Kernel Regression with Sparse Metric Learning
| Title | Kernel Regression with Sparse Metric Learning |
| Authors | Rongqing Huang, Shiliang Sun |
| Abstract | Kernel regression is a popular non-parametric fitting technique. It aims at learning a function which estimates the targets for test inputs as precise as possible. Generally, the function value for a test input is estimated by a weighted average of the surrounding training examples. The weights are typically computed by a distance-based kernel function and they strongly depend on the distances between examples. In this paper, we first review the latest developments of sparse metric learning and kernel regression. Then a novel kernel regression method involving sparse metric learning, which is called kernel regression with sparse metric learning (KR$_$SML), is proposed. The sparse kernel regression model is established by enforcing a mixed $(2,1)$-norm regularization over the metric matrix. It learns a Mahalanobis distance metric by a gradient descent procedure, which can simultaneously conduct dimensionality reduction and lead to good prediction results. Our work is the first to combine kernel regression with sparse metric learning. To verify the effectiveness of the proposed method, it is evaluated on 19 data sets for regression. Furthermore, the new method is also applied to solving practical problems of forecasting short-term traffic flows. In the end, we compare the proposed method with other three related kernel regression methods on all test data sets under two criterions. Experimental results show that the proposed method is much more competitive. |
| Tasks | Dimensionality Reduction, Metric Learning |
| Published | 2017-12-25 |
| URL | http://arxiv.org/abs/1712.09001v1 |
| http://arxiv.org/pdf/1712.09001v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-regression-with-sparse-metric-learning |
| Repo | |
| Framework | |
Systems of natural-language-facilitated human-robot cooperation: A review
| Title | Systems of natural-language-facilitated human-robot cooperation: A review |
| Authors | Rui Liu, Xiaoli Zhang |
| Abstract | Natural-language-facilitated human-robot cooperation (NLC), in which natural language (NL) is used to share knowledge between a human and a robot for conducting intuitive human-robot cooperation (HRC), is continuously developing in the recent decade. Currently, NLC is used in several robotic domains such as manufacturing, daily assistance and health caregiving. It is necessary to summarize current NLC-based robotic systems and discuss the future developing trends, providing helpful information for future NLC research. In this review, we first analyzed the driving forces behind the NLC research. Regarding to a robot s cognition level during the cooperation, the NLC implementations then were categorized into four types {NL-based control, NL-based robot training, NL-based task execution, NL-based social companion} for comparison and discussion. Last based on our perspective and comprehensive paper review, the future research trends were discussed. |
| Tasks | |
| Published | 2017-01-28 |
| URL | http://arxiv.org/abs/1701.08269v2 |
| http://arxiv.org/pdf/1701.08269v2.pdf | |
| PWC | https://paperswithcode.com/paper/systems-of-natural-language-facilitated-human |
| Repo | |
| Framework | |
PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training
| Title | PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training |
| Authors | Meng Li, Liangzhen Lai, Naveen Suda, Vikas Chandra, David Z. Pan |
| Abstract | Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services but suffer from potential privacy risks due to excessive user data collection. To enable cloud-based DNN training while protecting the data privacy simultaneously, we propose to leverage the intermediate representations of the data, which is achieved by splitting the DNNs and deploying them separately onto local platforms and the cloud. The local neural network (NN) is used to generate the feature representations. To avoid local training and protect data privacy, the local NN is derived from pre-trained NNs. The cloud NN is then trained based on the extracted intermediate representations for the target learning task. We validate the idea of DNN splitting by characterizing the dependency of privacy loss and classification accuracy on the local NN topology for a convolutional NN (CNN) based image classification task. Based on the characterization, we further propose PrivyNet to determine the local NN topology, which optimizes the accuracy of the target learning task under the constraints on privacy loss, local computation, and storage. The efficiency and effectiveness of PrivyNet are demonstrated with the CIFAR-10 dataset. |
| Tasks | Image Classification |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.06161v3 |
| http://arxiv.org/pdf/1709.06161v3.pdf | |
| PWC | https://paperswithcode.com/paper/privynet-a-flexible-framework-for-privacy |
| Repo | |
| Framework | |
Generating Descriptions with Grounded and Co-Referenced People
| Title | Generating Descriptions with Grounded and Co-Referenced People |
| Authors | Anna Rohrbach, Marcus Rohrbach, Siyu Tang, Seong Joon Oh, Bernt Schiele |
| Abstract | Learning how to generate descriptions of images or videos received major interest both in the Computer Vision and Natural Language Processing communities. While a few works have proposed to learn a grounding during the generation process in an unsupervised way (via an attention mechanism), it remains unclear how good the quality of the grounding is and whether it benefits the description quality. In this work we propose a movie description model which learns to generate description and jointly ground (localize) the mentioned characters as well as do visual co-reference resolution between pairs of consecutive sentences/clips. We also propose to use weak localization supervision through character mentions provided in movie descriptions to learn the character grounding. At training time, we first learn how to localize characters by relating their visual appearance to mentions in the descriptions via a semi-supervised approach. We then provide this (noisy) supervision into our description model which greatly improves its performance. Our proposed description model improves over prior work w.r.t. generated description quality and additionally provides grounding and local co-reference resolution. We evaluate it on the MPII Movie Description dataset using automatic and human evaluation measures and using our newly collected grounding and co-reference data for characters. |
| Tasks | |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01518v1 |
| http://arxiv.org/pdf/1704.01518v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-descriptions-with-grounded-and-co |
| Repo | |
| Framework | |
Estimating the resolution of real images
| Title | Estimating the resolution of real images |
| Authors | Ryuta Mizutani, Rino Saiga, Susumu Takekoshi, Chie Inomoto, Naoya Nakamura, Makoto Arai, Kenichi Oshima, Masanari Itokawa, Akihisa Takeuchi, Kentaro Uesugi, Yasuko Terada, Yoshio Suzuki |
| Abstract | Image resolvability is the primary concern in imaging. This paper reports an estimation of the full width at half maximum of the point spread function from a Fourier domain plot of real sample images by neither using test objects, nor defining a threshold criterion. We suggest that this method can be applied to any type of image, independently of the imaging modality. |
| Tasks | |
| Published | 2017-03-02 |
| URL | http://arxiv.org/abs/1703.00992v1 |
| http://arxiv.org/pdf/1703.00992v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-the-resolution-of-real-images |
| Repo | |
| Framework | |
