July 27, 2019

3377 words 16 mins read

Paper Group ANR 751

The identity of information: how deterministic dependencies constrain information synergy and redundancy. Crime Topic Modeling. A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising. High Efficient Reconstruction of Single-shot T2 Mapping from OverLapping-Echo Detachment Planar Imaging …

The identity of information: how deterministic dependencies constrain information synergy and redundancy


Title	The identity of information: how deterministic dependencies constrain information synergy and redundancy
Authors	Daniel Chicharro, Giuseppe Pica, Stefano Panzeri
Abstract	Understanding how different information sources together transmit information is crucial in many domains. For example, understanding the neural code requires characterizing how different neurons contribute unique, redundant, or synergistic pieces of information about sensory or behavioral variables. Williams and Beer (2010) proposed a partial information decomposition (PID) which separates the mutual information that a set of sources contains about a set of targets into nonnegative terms interpretable as these pieces. Quantifying redundancy requires assigning an identity to different information pieces, to assess when information is common across sources. Harder et al. (2013) proposed an identity axiom stating that there cannot be redundancy between two independent sources about a copy of themselves. However, Bertschinger et al. (2012) showed that with a deterministically related sources-target copy this axiom is incompatible with ensuring PID nonnegativity. Here we study systematically the effect of deterministic target-sources dependencies. We introduce two synergy stochasticity axioms that generalize the identity axiom, and we derive general expressions separating stochastic and deterministic PID components. Our analysis identifies how negative terms can originate from deterministic dependencies and shows how different assumptions on information identity, implicit in the stochasticity and identity axioms, determine the PID structure. The implications for studying neural coding are discussed.
Tasks
Published	2017-11-13
URL	http://arxiv.org/abs/1711.11408v1
PDF	http://arxiv.org/pdf/1711.11408v1.pdf
PWC	https://paperswithcode.com/paper/the-identity-of-information-how-deterministic
Repo
Framework

Crime Topic Modeling


Title	Crime Topic Modeling
Authors	Da Kuang, P. Jeffrey Brantingham, Andrea L. Bertozzi
Abstract	The classification of crime into discrete categories entails a massive loss of information. Crimes emerge out of a complex mix of behaviors and situations, yet most of these details cannot be captured by singular crime type labels. This information loss impacts our ability to not only understand the causes of crime, but also how to develop optimal crime prevention strategies. We apply machine learning methods to short narrative text descriptions accompanying crime records with the goal of discovering ecologically more meaningful latent crime classes. We term these latent classes “crime topics” in reference to text-based topic modeling methods that produce them. We use topic distributions to measure clustering among formally recognized crime types. Crime topics replicate broad distinctions between violent and property crime, but also reveal nuances linked to target characteristics, situational conditions and the tools and methods of attack. Formal crime types are not discrete in topic space. Rather, crime types are distributed across a range of crime topics. Similarly, individual crime topics are distributed across a range of formal crime types. Key ecological groups include identity theft, shoplifting, burglary and theft, car crimes and vandalism, criminal threats and confidence crimes, and violent crimes. Though not a replacement for formal legal crime classifications, crime topics provide a unique window into the heterogeneous causal processes underlying crime.
Tasks
Published	2017-01-05
URL	http://arxiv.org/abs/1701.01505v2
PDF	http://arxiv.org/pdf/1701.01505v2.pdf
PWC	https://paperswithcode.com/paper/crime-topic-modeling
Repo
Framework

A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising


Title	A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising
Authors	Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov
Abstract	A learning-based framework for representation of domain-specific images is proposed where joint compression and denoising can be done using a VQ-based multi-layer network. While it learns to compress the images from a training set, the compression performance is very well generalized on images from a test set. Moreover, when fed with noisy versions of the test set, since it has priors from clean images, the network also efficiently denoises the test images during the reconstruction. The proposed framework is a regularized version of the Residual Quantization (RQ) where at each stage, the quantization error from the previous stage is further quantized. Instead of codebook learning from the k-means which over-trains for high-dimensional vectors, we show that only generating the codewords from a random, but properly regularized distribution suffices to compress the images globally and without the need to resort to patch-based division of images. The experiments are done on the \textit{CroppedYale-B} set of facial images and the method is compared with the JPEG-2000 codec for compression and BM3D for denoising, showing promising results.
Tasks	Denoising, Quantization
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02194v1
PDF	http://arxiv.org/pdf/1707.02194v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-layer-image-representation-using
Repo
Framework

High Efficient Reconstruction of Single-shot T2 Mapping from OverLapping-Echo Detachment Planar Imaging Based on Deep Residual Network


Title	High Efficient Reconstruction of Single-shot T2 Mapping from OverLapping-Echo Detachment Planar Imaging Based on Deep Residual Network
Authors	Congbo Cai, Yiqing Zeng, Chao Wang, Shuhui Cai, Jun Zhang, Zhong Chen, Xinghao Ding, Jianhui Zhong
Abstract	Purpose: An end-to-end deep convolutional neural network (CNN) based on deep residual network (ResNet) was proposed to efficiently reconstruct reliable T2 mapping from single-shot OverLapping-Echo Detachment (OLED) planar imaging. Methods: The training dataset was obtained from simulations carried out on SPROM software developed by our group. The relationship between the original OLED image containing two echo signals and the corresponded T2 mapping was learned by ResNet training. After the ResNet was trained, it was applied to reconstruct the T2 mapping from simulation and in vivo human brain data. Results: Though the ResNet was trained entirely on simulated data, the trained network was generalized well to real human brain data. The results from simulation and in vivo human brain experiments show that the proposed method significantly outperformed the echo-detachment-based method. Reliable T2 mapping was achieved within tens of milliseconds after the network had been trained while the echo-detachment-based OLED reconstruction method took minutes. Conclusion: The proposed method will greatly facilitate real-time dynamic and quantitative MR imaging via OLED sequence, and ResNet has the potential to reconstruct images from complex MRI sequence efficiently.
Tasks
Published	2017-08-17
URL	http://arxiv.org/abs/1708.05170v1
PDF	http://arxiv.org/pdf/1708.05170v1.pdf
PWC	https://paperswithcode.com/paper/high-efficient-reconstruction-of-single-shot
Repo
Framework

A Learning-to-Infer Method for Real-Time Power Grid Multi-Line Outage Identification


Title	A Learning-to-Infer Method for Real-Time Power Grid Multi-Line Outage Identification
Authors	Yue Zhao, Jianshu Chen, H. Vincent Poor
Abstract	Identifying a potentially large number of simultaneous line outages in power transmission networks in real time is a computationally hard problem. This is because the number of hypotheses grows exponentially with the network size. A new “Learning-to-Infer” method is developed for efficient inference of every line status in the network. Optimizing the line outage detector is transformed to and solved as a discriminative learning problem based on Monte Carlo samples generated with power flow simulations. A major advantage of the developed Learning-to-Infer method is that the labeled data used for training can be generated in an arbitrarily large amount rapidly and at very little cost. As a result, the power of offline training is fully exploited to learn very complex classifiers for effective real-time multi-line outage identification. The proposed methods are evaluated in the IEEE 30, 118 and 300 bus systems. Excellent performance in identifying multi-line outages in real time is achieved with a reasonably small amount of data.
Tasks
Published	2017-10-21
URL	https://arxiv.org/abs/1710.07818v2
PDF	https://arxiv.org/pdf/1710.07818v2.pdf
PWC	https://paperswithcode.com/paper/a-learning-to-infer-method-for-real-time
Repo
Framework

An efficient SAT formulation for learning multiple criteria non-compensatory sorting rules from examples


Title	An efficient SAT formulation for learning multiple criteria non-compensatory sorting rules from examples
Authors	K. Belahcène, C. Labreuche, N. Maudet, V. Mousseau, W. Ouerdane
Abstract	The literature on Multiple Criteria Decision Analysis (MCDA) proposes several methods in order to sort alternatives evaluated on several attributes into ordered classes. Non Compensatory Sorting models (NCS) assign alternatives to classes based on the way they compare to multicriteria profiles separating the consecutive classes. Previous works have proposed approaches to learn the parameters of a NCS model based on a learning set. Exact approaches based on mixed integer linear programming ensures that the learning set is best restored, but can only handle datasets of limited size. Heuristic approaches can handle large learning sets, but do not provide any guarantee about the inferred model. In this paper, we propose an alternative formulation to learn a NCS model. This formulation, based on a SAT problem, guarantees to find a model fully consistent with the learning set (whenever it exists), and is computationally much more efficient than existing exact MIP approaches.
Tasks
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10098v1
PDF	http://arxiv.org/pdf/1710.10098v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-sat-formulation-for-learning
Repo
Framework

VANETs Meet Autonomous Vehicles: A Multimodal 3D Environment Learning Approach


Title	VANETs Meet Autonomous Vehicles: A Multimodal 3D Environment Learning Approach
Authors	Yassine Maalej, Sameh Sorour, Ahmed Abdel-Rahim, Mohsen Guizani
Abstract	In this paper, we design a multimodal framework for object detection, recognition and mapping based on the fusion of stereo camera frames, point cloud Velodyne Lidar scans, and Vehicle-to-Vehicle (V2V) Basic Safety Messages (BSMs) exchanged using Dedicated Short Range Communication (DSRC). We merge the key features of rich texture descriptions of objects from 2D images, depth and distance between objects provided by 3D point cloud and awareness of hidden vehicles from BSMs’ 3D information. We present a joint pixel to point cloud and pixel to V2V correspondences of objects in frames from the Kitti Vision Benchmark Suite by using a semi-supervised manifold alignment approach to achieve camera-Lidar and camera-V2V mapping of their recognized objects that have the same underlying manifold.
Tasks	Autonomous Vehicles, Object Detection
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08624v1
PDF	http://arxiv.org/pdf/1705.08624v1.pdf
PWC	https://paperswithcode.com/paper/vanets-meet-autonomous-vehicles-a-multimodal
Repo
Framework

Robust Communication-Optimal Distributed Clustering Algorithms


Title	Robust Communication-Optimal Distributed Clustering Algorithms
Authors	Pranjal Awasthi, Ainesh Bakshi, Maria-Florina Balcan, Colin White, David Woodruff
Abstract	In this work, we study the $k$-median and $k$-means clustering problems when the data is distributed across many servers and can contain outliers. While there has been a lot of work on these problems for worst-case instances, we focus on gaining a finer understanding through the lens of beyond worst-case analysis. Our main motivation is the following: for many applications such as clustering proteins by function or clustering communities in a social network, there is some unknown target clustering, and the hope is that running a $k$-median or $k$-means algorithm will produce clusterings which are close to matching the target clustering. Worst-case results can guarantee constant factor approximations to the optimal $k$-median or $k$-means objective value, but not closeness to the target clustering. Our first result is a distributed algorithm which returns a near-optimal clustering assuming a natural notion of stability, namely, approximation stability [Balcan et. al 2013], even when a constant fraction of the data are outliers. The communication complexity is $\tilde O(sk+z)$ where $s$ is the number of machines, $k$ is the number of clusters, and $z$ is the number of outliers. Next, we show this amount of communication cannot be improved even in the setting when the input satisfies various non-worst-case assumptions. We give a matching $\Omega(sk+z)$ lower bound on the communication required both for approximating the optimal $k$-means or $k$-median cost up to any constant, and for returning a clustering that is close to the target clustering in Hamming distance. These lower bounds hold even when the data satisfies approximation stability or other common notions of stability, and the cluster sizes are balanced. Therefore, $\Omega(sk+z)$ is a communication bottleneck, even for real-world instances.
Tasks
Published	2017-03-02
URL	http://arxiv.org/abs/1703.00830v3
PDF	http://arxiv.org/pdf/1703.00830v3.pdf
PWC	https://paperswithcode.com/paper/robust-communication-optimal-distributed
Repo
Framework

Unsupervised object segmentation in video by efficient selection of highly probable positive features


Title	Unsupervised object segmentation in video by efficient selection of highly probable positive features
Authors	Emanuela Haller, Marius Leordeanu
Abstract	We address an essential problem in computer vision, that of unsupervised object segmentation in video, where a main object of interest in a video sequence should be automatically separated from its background. An efficient solution to this task would enable large-scale video interpretation at a high semantic level in the absence of the costly manually labeled ground truth. We propose an efficient unsupervised method for generating foreground object soft-segmentation masks based on automatic selection and learning from highly probable positive features. We show that such features can be selected efficiently by taking into consideration the spatio-temporal, appearance and motion consistency of the object during the whole observed sequence. We also emphasize the role of the contrasting properties between the foreground object and its background. Our model is created in two stages: we start from pixel level analysis, on top of which we add a regression model trained on a descriptor that considers information over groups of pixels and is both discriminative and invariant to many changes that the object undergoes throughout the video. We also present theoretical properties of our unsupervised learning method, that under some mild constraints is guaranteed to learn a correct discriminative classifier even in the unsupervised case. Our method achieves competitive and even state of the art results on the challenging Youtube-Objects and SegTrack datasets, while being at least one order of magnitude faster than the competition. We believe that the competitive performance of our method in practice, along with its theoretical properties, constitute an important step towards solving unsupervised discovery in video.
Tasks	Semantic Segmentation
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05674v1
PDF	http://arxiv.org/pdf/1704.05674v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-object-segmentation-in-video-by
Repo
Framework

Learning Registered Point Processes from Idiosyncratic Observations


Title	Learning Registered Point Processes from Idiosyncratic Observations
Authors	Hongteng Xu, Lawrence Carin, Hongyuan Zha
Abstract	A parametric point process model is developed, with modeling based on the assumption that sequential observations often share latent phenomena, while also possessing idiosyncratic effects. An alternating optimization method is proposed to learn a “registered” point process that accounts for shared structure, as well as “warping” functions that characterize idiosyncratic aspects of each observed sequence. Under reasonable constraints, in each iteration we update the sample-specific warping functions by solving a set of constrained nonlinear programming problems in parallel, and update the model by maximum likelihood estimation. The justifiability, complexity and robustness of the proposed method are investigated in detail, and the influence of sequence stitching on the learning results is examined empirically. Experiments on both synthetic and real-world data demonstrate that the method yields explainable point process models, achieving encouraging results compared to state-of-the-art methods.
Tasks	Point Processes
Published	2017-10-03
URL	http://arxiv.org/abs/1710.01410v3
PDF	http://arxiv.org/pdf/1710.01410v3.pdf
PWC	https://paperswithcode.com/paper/learning-registered-point-processes-from
Repo
Framework

Deep Hyperspherical Learning


Title	Deep Hyperspherical Learning
Authors	Weiyang Liu, Yan-Ming Zhang, Xingguo Li, Zhiding Yu, Bo Dai, Tuo Zhao, Le Song
Abstract	Convolution as inner product has been the founding basis of convolutional neural networks (CNNs) and the key to end-to-end visual representation learning. Benefiting from deeper architectures, recent CNNs have demonstrated increasingly strong representation abilities. Despite such improvement, the increased depth and larger parameter space have also led to challenges in properly training a network. In light of such challenges, we propose hyperspherical convolution (SphereConv), a novel learning framework that gives angular representations on hyperspheres. We introduce SphereNet, deep hyperspherical convolution networks that are distinct from conventional inner product based convolutional networks. In particular, SphereNet adopts SphereConv as its basic convolution operator and is supervised by generalized angular softmax loss - a natural loss formulation under SphereConv. We show that SphereNet can effectively encode discriminative representation and alleviate training difficulty, leading to easier optimization, faster convergence and comparable (even better) classification accuracy over convolutional counterparts. We also provide some theoretical insights for the advantages of learning on hyperspheres. In addition, we introduce the learnable SphereConv, i.e., a natural improvement over prefixed SphereConv, and SphereNorm, i.e., hyperspherical learning as a normalization method. Experiments have verified our conclusions.
Tasks	Representation Learning
Published	2017-11-08
URL	http://arxiv.org/abs/1711.03189v5
PDF	http://arxiv.org/pdf/1711.03189v5.pdf
PWC	https://paperswithcode.com/paper/deep-hyperspherical-learning
Repo
Framework

Locating 3D Object Proposals: A Depth-Based Online Approach


Title	Locating 3D Object Proposals: A Depth-Based Online Approach
Authors	Ramanpreet Singh Pahwa, Jiangbo Lu, Nianjuan Jiang, Tian Tsong Ng, Minh N. Do
Abstract	2D object proposals, quickly detected regions in an image that likely contain an object of interest, are an effective approach for improving the computational efficiency and accuracy of object detection in color images. In this work, we propose a novel online method that generates 3D object proposals in a RGB-D video sequence. Our main observation is that depth images provide important information about the geometry of the scene. Diverging from the traditional goal of 2D object proposals to provide a high recall (lots of 2D bounding boxes near potential objects), we aim for precise 3D proposals. We leverage on depth information per frame and multi-view scene information to obtain accurate 3D object proposals. Using efficient but robust registration enables us to combine multiple frames of a scene in near real time and generate 3D bounding boxes for potential 3D regions of interest. Using standard metrics, such as Precision-Recall curves and F-measure, we show that the proposed approach is significantly more accurate than the current state-of-the-art techniques. Our online approach can be integrated into SLAM based video processing for quick 3D object localization. Our method takes less than a second in MATLAB on the UW-RGBD scene dataset on a single thread CPU and thus, has potential to be used in low-power chips in Unmanned Aerial Vehicles (UAVs), quadcopters, and drones.
Tasks	Object Detection, Object Localization
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02653v1
PDF	http://arxiv.org/pdf/1709.02653v1.pdf
PWC	https://paperswithcode.com/paper/locating-3d-object-proposals-a-depth-based
Repo
Framework

Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation


Title	Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
Authors	Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann, Lars Petersson, Jose M. Alvarez, Stephen Gould
Abstract	Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, this leads to poor localization accuracy. This problem, however, was alleviated by making use of objectness priors to generate foreground/background masks. Unfortunately these priors either require pixel-level annotations/bounding boxes, or still yield inaccurate object boundaries. Here, we propose a novel method to extract accurate masks from networks pre-trained for the task of object recognition, thus forgoing external objectness modules. We first show how foreground/background masks can be obtained from the activations of higher-level convolutional layers of a network. We then show how to obtain multi-class masks by the fusion of foreground/background ones with information extracted from a weakly-supervised localization network. Our experiments evidence that exploiting these masks in conjunction with a weakly-supervised training loss yields state-of-the-art tag-based weakly-supervised semantic segmentation results.
Tasks	Object Recognition, Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2017-06-06
URL	http://arxiv.org/abs/1706.02189v1
PDF	http://arxiv.org/pdf/1706.02189v1.pdf
PWC	https://paperswithcode.com/paper/incorporating-network-built-in-priors-in
Repo
Framework

Deep Neural Machine Translation with Linear Associative Unit


Title	Deep Neural Machine Translation with Linear Associative Unit
Authors	Mingxuan Wang, Zhengdong Lu, Jie Zhou, Qun Liu
Abstract	Deep Neural Networks (DNNs) have provably enhanced the state-of-the-art Neural Machine Translation (NMT) with their capability in modeling complex functions and capturing complex linguistic structures. However NMT systems with deep architecture in their encoder or decoder RNNs often suffer from severe gradient diffusion due to the non-linear recurrent activations, which often make the optimization much more difficult. To address this problem we propose novel linear associative units (LAU) to reduce the gradient propagation length inside the recurrent unit. Different from conventional approaches (LSTM unit and GRU), LAUs utilizes linear associative connections between input and output of the recurrent unit, which allows unimpeded information flow through both space and time direction. The model is quite simple, but it is surprisingly effective. Our empirical study on Chinese-English translation shows that our model with proper configuration can improve by 11.7 BLEU upon Groundhog and the best reported results in the same setting. On WMT14 English-German task and a larger WMT14 English-French task, our model achieves comparable results with the state-of-the-art.
Tasks	Machine Translation
Published	2017-05-02
URL	http://arxiv.org/abs/1705.00861v1
PDF	http://arxiv.org/pdf/1705.00861v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-machine-translation-with-linear
Repo
Framework

Block-Parallel IDA* for GPUs (Extended Manuscript)


Title	Block-Parallel IDA* for GPUs (Extended Manuscript)
Authors	Satoru Horie, Alex Fukunaga
Abstract	We investigate GPU-based parallelization of Iterative-Deepening A* (IDA). We show that straightforward thread-based parallelization techniques which were previously proposed for massively parallel SIMD processors perform poorly due to warp divergence and load imbalance. We propose Block-Parallel IDA (BPIDA), which assigns the search of a subtree to a block (a group of threads with access to fast shared memory) rather than a thread. On the 15-puzzle, BPIDA on a NVIDIA GRID K520 with 1536 CUDA cores achieves a speedup of 4.98 compared to a highly optimized sequential IDA* implementation on a Xeon E5-2670 core.
Tasks
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02843v1
PDF	http://arxiv.org/pdf/1705.02843v1.pdf
PWC	https://paperswithcode.com/paper/block-parallel-ida-for-gpus-extended
Repo
Framework