July 27, 2019

3160 words 15 mins read

Paper Group ANR 547

Learning Rates for Kernel-Based Expectile Regression. Freeway Merging in Congested Traffic based on Multipolicy Decision Making with Passive Actor Critic. Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise. Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory. Saliency G …

Learning Rates for Kernel-Based Expectile Regression


Title	Learning Rates for Kernel-Based Expectile Regression
Authors	Muhammad Farooq, Ingo Steinwart
Abstract	Conditional expectiles are becoming an increasingly important tool in finance as well as in other areas of applications. We analyse a support vector machine type approach for estimating conditional expectiles and establish learning rates that are minimax optimal modulo a logarithmic factor if Gaussian RBF kernels are used and the desired expectile is smooth in a Besov sense. As a special case, our learning rates improve the best known rates for kernel-based least squares regression in this scenario. Key ingredients of our statistical analysis are a general calibration inequality for the asymmetric least squares loss, a corresponding variance bound as well as an improved entropy number bound for Gaussian RBF kernels.
Tasks	Calibration
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07552v2
PDF	http://arxiv.org/pdf/1702.07552v2.pdf
PWC	https://paperswithcode.com/paper/learning-rates-for-kernel-based-expectile
Repo
Framework

Freeway Merging in Congested Traffic based on Multipolicy Decision Making with Passive Actor Critic


Title	Freeway Merging in Congested Traffic based on Multipolicy Decision Making with Passive Actor Critic
Authors	Tomoki Nishi, Prashant Doshi, Danil Prokhorov
Abstract	Freeway merging in congested traffic is a significant challenge toward fully automated driving. Merging vehicles need to decide not only how to merge into a spot, but also where to merge. We present a method for the freeway merging based on multi-policy decision making with a reinforcement learning method called {\em passive actor-critic} (pAC), which learns with less knowledge of the system and without active exploration. The method selects a merging spot candidate by using the state value learned with pAC. We evaluate our method using real traffic data. Our experiments show that pAC achieves 92% success rate to merge into a freeway, which is comparable to human decision making.
Tasks	Decision Making
Published	2017-07-14
URL	http://arxiv.org/abs/1707.04489v1
PDF	http://arxiv.org/pdf/1707.04489v1.pdf
PWC	https://paperswithcode.com/paper/freeway-merging-in-congested-traffic-based-on
Repo
Framework

Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise


Title	Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise
Authors	Soumitro Chakrabarty, Emanuël A. P. Habets
Abstract	The problem of multi-speaker localization is formulated as a multi-class multi-label classification problem, which is solved using a convolutional neural network (CNN) based source localization method. Utilizing the common assumption of disjoint speaker activities, we propose a novel method to train the CNN using synthesized noise signals. The proposed localization method is evaluated for two speakers and compared to a well-known steered response power method.
Tasks	Multi-Label Classification
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04276v1
PDF	http://arxiv.org/pdf/1712.04276v1.pdf
PWC	https://paperswithcode.com/paper/multi-speaker-localization-using
Repo
Framework

Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory


Title	Efficient Algorithms for Searching the Minimum Information Partition in Integrated Information Theory
Authors	Jun Kitazono, Ryota Kanai, Masafumi Oizumi
Abstract	The ability to integrate information in the brain is considered to be an essential property for cognition and consciousness. Integrated Information Theory (IIT) hypothesizes that the amount of integrated information ($\Phi$) in the brain is related to the level of consciousness. IIT proposes that to quantify information integration in a system as a whole, integrated information should be measured across the partition of the system at which information loss caused by partitioning is minimized, called the Minimum Information Partition (MIP). The computational cost for exhaustively searching for the MIP grows exponentially with system size, making it difficult to apply IIT to real neural data. It has been previously shown that if a measure of $\Phi$ satisfies a mathematical property, submodularity, the MIP can be found in a polynomial order by an optimization algorithm. However, although the first version of $\Phi$ is submodular, the later versions are not. In this study, we empirically explore to what extent the algorithm can be applied to the non-submodular measures of $\Phi$ by evaluating the accuracy of the algorithm in simulated data and real neural data. We find that the algorithm identifies the MIP in a nearly perfect manner even for the non-submodular measures. Our results show that the algorithm allows us to measure $\Phi$ in large systems within a practical amount of time.
Tasks
Published	2017-12-19
URL	http://arxiv.org/abs/1712.06745v2
PDF	http://arxiv.org/pdf/1712.06745v2.pdf
PWC	https://paperswithcode.com/paper/efficient-algorithms-for-searching-the
Repo
Framework

Saliency Guided End-to-End Learning for Weakly Supervised Object Detection


Title	Saliency Guided End-to-End Learning for Weakly Supervised Object Detection
Authors	Baisheng Lai, Xiaojin Gong
Abstract	Weakly supervised object detection (WSOD), which is the problem of learning detectors using only image-level labels, has been attracting more and more interest. However, this problem is quite challenging due to the lack of location supervision. To address this issue, this paper integrates saliency into a deep architecture, in which the location in- formation is explored both explicitly and implicitly. Specifically, we select highly confident object pro- posals under the guidance of class-specific saliency maps. The location information, together with semantic and saliency information, of the selected proposals are then used to explicitly supervise the network by imposing two additional losses. Meanwhile, a saliency prediction sub-network is built in the architecture. The prediction results are used to implicitly guide the localization procedure. The entire network is trained end-to-end. Experiments on PASCAL VOC demonstrate that our approach outperforms all state-of-the-arts.
Tasks	Object Detection, Saliency Prediction, Weakly Supervised Object Detection
Published	2017-06-21
URL	http://arxiv.org/abs/1706.06768v1
PDF	http://arxiv.org/pdf/1706.06768v1.pdf
PWC	https://paperswithcode.com/paper/saliency-guided-end-to-end-learning-for
Repo
Framework

A robust approach for tree segmentation in deciduous forests using small-footprint airborne LiDAR data


Title	A robust approach for tree segmentation in deciduous forests using small-footprint airborne LiDAR data
Authors	Hamid Hamraz, Marco A. Contreras, Jun Zhang
Abstract	This paper presents a non-parametric approach for segmenting trees from airborne LiDAR data in deciduous forests. Based on the LiDAR point cloud, the approach collects crown information such as steepness and height on-the-fly to delineate crown boundaries, and most importantly, does not require a priori assumptions of crown shape and size. The approach segments trees iteratively starting from the tallest within a given area to the smallest until all trees have been segmented. To evaluate its performance, the approach was applied to the University of Kentucky Robinson Forest, a deciduous closed-canopy forest with complex terrain and vegetation conditions. The approach identified 94% of dominant and co-dominant trees with a false detection rate of 13%. About 62% of intermediate, overtopped, and dead trees were also detected with a false detection rate of 15%. The overall segmentation accuracy was 77%. Correlations of the segmentation scores of the proposed approach with local terrain and stand metrics was not significant, which is likely an indication of the robustness of the approach as results are not sensitive to the differences in terrain and stand structures.
Tasks
Published	2017-01-01
URL	http://arxiv.org/abs/1701.00198v1
PDF	http://arxiv.org/pdf/1701.00198v1.pdf
PWC	https://paperswithcode.com/paper/a-robust-approach-for-tree-segmentation-in
Repo
Framework

ECO-AMLP: A Decision Support System using an Enhanced Class Outlier with Automatic Multilayer Perceptron for Diabetes Prediction


Title	ECO-AMLP: A Decision Support System using an Enhanced Class Outlier with Automatic Multilayer Perceptron for Diabetes Prediction
Authors	Maham Jahangir, Hammad Afzal, Mehreen Ahmed, Khawar Khurshid, Raheel Nawaz
Abstract	With advanced data analytical techniques, efforts for more accurate decision support systems for disease prediction are on rise. Surveys by World Health Organization (WHO) indicate a great increase in number of diabetic patients and related deaths each year. Early diagnosis of diabetes is a major concern among researchers and practitioners. The paper presents an application of \textit{Automatic Multilayer Perceptron }which\textit{ }is combined with an outlier detection method \textit{Enhanced Class Outlier Detection using distance based algorithm }to create a prediction framework named as Enhanced Class Outlier with Automatic Multi layer Perceptron (ECO-AMLP). A series of experiments are performed on publicly available Pima Indian Diabetes Dataset to compare ECO-AMLP with other individual classifiers as well as ensemble based methods. The outlier technique used in our framework gave better results as compared to other pre-processing and classification techniques. Finally, the results are compared with other state-of-the-art methods reported in literature for diabetes prediction on PIDD and achieved accuracy of 88.7% bests all other reported studies.
Tasks	Diabetes Prediction, Disease Prediction, Outlier Detection
Published	2017-06-23
URL	http://arxiv.org/abs/1706.07679v1
PDF	http://arxiv.org/pdf/1706.07679v1.pdf
PWC	https://paperswithcode.com/paper/eco-amlp-a-decision-support-system-using-an
Repo
Framework

Energy-efficient Amortized Inference with Cascaded Deep Classifiers


Title	Energy-efficient Amortized Inference with Cascaded Deep Classifiers
Authors	Jiaqi Guan, Yang Liu, Qiang Liu, Jian Peng
Abstract	Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that optimizes the prediction accuracy and energy cost simultaneously, thus enabling effective cost-accuracy trade-off at test time. In our framework, each data instance is pushed into a cascade of deep neural networks with increasing sizes, and a selection module is used to sequentially determine when a sufficiently accurate classifier can be used for this data instance. The cascade of neural networks and the selection module are jointly trained in an end-to-end fashion by the REINFORCE algorithm to optimize a trade-off between the computational cost and the predictive accuracy. Our method is able to simultaneously improve the accuracy and efficiency by learning to assign easy instances to fast yet sufficiently accurate classifiers to save computation and energy cost, while assigning harder instances to deeper and more powerful classifiers to ensure satisfiable accuracy. With extensive experiments on several image classification datasets using cascaded ResNet classifiers, we demonstrate that our method outperforms the standard well-trained ResNets in accuracy but only requires less than 20% and 50% FLOPs cost on the CIFAR-10/100 datasets and 66% on the ImageNet dataset, respectively.
Tasks	Image Classification
Published	2017-10-10
URL	http://arxiv.org/abs/1710.03368v1
PDF	http://arxiv.org/pdf/1710.03368v1.pdf
PWC	https://paperswithcode.com/paper/energy-efficient-amortized-inference-with
Repo
Framework

ARREST: A RSSI Based Approach for Mobile Sensing and Tracking of a Moving Object


Title	ARREST: A RSSI Based Approach for Mobile Sensing and Tracking of a Moving Object
Authors	Pradipta Ghosh, Jason A. Tran, Bhaskar Krishnamachari
Abstract	We present Autonomous Rssi based RElative poSitioning and Tracking (ARREST), a new robotic sensing system for tracking and following a moving, RF-emitting object, which we refer to as the Leader, solely based on signal strength information. This kind of system can expand the horizon of autonomous mobile tracking and distributed robotics into many scenarios with limited visibility such as nighttime, dense forests, and cluttered environments. Our proposed tracking agent, which we refer to as the TrackBot, uses a single rotating, off-the-shelf, directional antenna, novel angle and relative speed estimation algorithms, and Kalman filtering to continually estimate the relative position of the Leader with decimeter level accuracy (which is comparable to a state-of-the-art multiple access point based RF-localization system) and the relative speed of the Leader with accuracy on the order of 1 m/s. The TrackBot feeds the relative position and speed estimates into a Linear Quadratic Gaussian (LQG) controller to generate a set of control outputs to control the orientation and the movement of the TrackBot. We perform an extensive set of real world experiments with a full-fledged prototype to demonstrate that the TrackBot is able to stay within 5m of the Leader with: (1) more than $99%$ probability in line of sight scenarios, and (2) more than $70%$ probability in no line of sight scenarios, when it moves 1.8X faster than the Leader. For ground truth estimation in real world experiments, we also developed an integrated TDoA based distance and angle estimation system with centimeter level localization accuracy in line of sight scenarios. While providing a first proof of concept, our work opens the door to future research aimed at further improvements of autonomous RF-based tracking.
Tasks
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05493v2
PDF	http://arxiv.org/pdf/1707.05493v2.pdf
PWC	https://paperswithcode.com/paper/arrest-a-rssi-based-approach-for-mobile
Repo
Framework

Inverse Reinforcement Learning with Conditional Choice Probabilities


Title	Inverse Reinforcement Learning with Conditional Choice Probabilities
Authors	Mohit Sharma, Kris M. Kitani, Joachim Groeger
Abstract	We make an important connection to existing results in econometrics to describe an alternative formulation of inverse reinforcement learning (IRL). In particular, we describe an algorithm using Conditional Choice Probabilities (CCP), which are maximum likelihood estimates of the policy estimated from expert demonstrations, to solve the IRL problem. Using the language of structural econometrics, we re-frame the optimal decision problem and introduce an alternative representation of value functions due to (Hotz and Miller 1993). In addition to presenting the theoretical connections that bridge the IRL literature between Economics and Robotics, the use of CCPs also has the practical benefit of reducing the computational cost of solving the IRL problem. Specifically, under the CCP representation, we show how one can avoid repeated calls to the dynamic programming subroutine typically used in IRL. We show via extensive experimentation on standard IRL benchmarks that CCP-IRL is able to outperform MaxEnt-IRL, with as much as a 5x speedup and without compromising on the quality of the recovered reward function.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07597v1
PDF	http://arxiv.org/pdf/1709.07597v1.pdf
PWC	https://paperswithcode.com/paper/inverse-reinforcement-learning-with
Repo
Framework

Coupled Deep Learning for Heterogeneous Face Recognition


Title	Coupled Deep Learning for Heterogeneous Face Recognition
Authors	Xiang Wu, Lingxiao Song, Ran He, Tieniu Tan
Abstract	Heterogeneous face matching is a challenge issue in face recognition due to large domain difference as well as insufficient pairwise images in different modalities during training. This paper proposes a coupled deep learning (CDL) approach for the heterogeneous face matching. CDL seeks a shared feature space in which the heterogeneous face matching problem can be approximately treated as a homogeneous face matching problem. The objective function of CDL mainly includes two parts. The first part contains a trace norm and a block-diagonal prior as relevance constraints, which not only make unpaired images from multiple modalities be clustered and correlated, but also regularize the parameters to alleviate overfitting. An approximate variational formulation is introduced to deal with the difficulties of optimizing low-rank constraint directly. The second part contains a cross modal ranking among triplet domain specific images to maximize the margin for different identities and increase data for a small amount of training samples. Besides, an alternating minimization method is employed to iteratively update the parameters of CDL. Experimental results show that CDL achieves better performance on the challenging CASIA NIR-VIS 2.0 face recognition database, the IIIT-D Sketch database, the CUHK Face Sketch (CUFS), and the CUHK Face Sketch FERET (CUFSF), which significantly outperforms state-of-the-art heterogeneous face recognition methods.
Tasks	Face Recognition, Heterogeneous Face Recognition
Published	2017-04-08
URL	http://arxiv.org/abs/1704.02450v2
PDF	http://arxiv.org/pdf/1704.02450v2.pdf
PWC	https://paperswithcode.com/paper/coupled-deep-learning-for-heterogeneous-face
Repo
Framework

A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning


Title	A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learning
Authors	Shafin Rahman, Salman H. Khan, Fatih Porikli
Abstract	Prevalent techniques in zero-shot learning do not generalize well to other related problem scenarios. Here, we present a unified approach for conventional zero-shot, generalized zero-shot and few-shot learning problems. Our approach is based on a novel Class Adapting Principal Directions (CAPD) concept that allows multiple embeddings of image features into a semantic space. Given an image, our method produces one principal direction for each seen class. Then, it learns how to combine these directions to obtain the principal direction for each unseen class such that the CAPD of the test image is aligned with the semantic embedding of the true class, and opposite to the other classes. This allows efficient and class-adaptive information transfer from seen to unseen classes. In addition, we propose an automatic process for selection of the most useful seen classes for each unseen class to achieve robustness in zero-shot learning. Our method can update the unseen CAPD taking the advantages of few unseen images to work in a few-shot learning scenario. Furthermore, our method can generalize the seen CAPDs by estimating seen-unseen diversity that significantly improves the performance of generalized zero-shot learning. Our extensive evaluations demonstrate that the proposed approach consistently achieves superior performance in zero-shot, generalized zero-shot and few/one-shot learning problems.
Tasks	Few-Shot Learning, One-Shot Learning, Zero-Shot Learning
Published	2017-06-27
URL	http://arxiv.org/abs/1706.08653v2
PDF	http://arxiv.org/pdf/1706.08653v2.pdf
PWC	https://paperswithcode.com/paper/a-unified-approach-for-conventional-zero-shot
Repo
Framework

Unifying local and non-local signal processing with graph CNNs


Title	Unifying local and non-local signal processing with graph CNNs
Authors	Gilles Puy, Srdan Kitic, Patrick Pérez
Abstract	This paper deals with the unification of local and non-local signal processing on graphs within a single convolutional neural network (CNN) framework. Building upon recent works on graph CNNs, we propose to use convolutional layers that take as inputs two variables, a signal and a graph, allowing the network to adapt to changes in the graph structure. In this article, we explain how this framework allows us to design a novel method to perform style transfer.
Tasks	Style Transfer
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07759v2
PDF	http://arxiv.org/pdf/1702.07759v2.pdf
PWC	https://paperswithcode.com/paper/unifying-local-and-non-local-signal
Repo
Framework

On consistent vertex nomination schemes


Title	On consistent vertex nomination schemes
Authors	Vince Lyzinski, Keith Levin, Carey E. Priebe
Abstract	Given a vertex of interest in a network $G_1$, the vertex nomination problem seeks to find the corresponding vertex of interest (if it exists) in a second network $G_2$. A vertex nomination scheme produces a list of the vertices in $G_2$, ranked according to how likely they are judged to be the corresponding vertex of interest in $G_2$. The vertex nomination problem and related information retrieval tasks have attracted much attention in the machine learning literature, with numerous applications to social and biological networks. However, the current framework has often been confined to a comparatively small class of network models, and the concept of statistically consistent vertex nomination schemes has been only shallowly explored. In this paper, we extend the vertex nomination problem to a very general statistical model of graphs. Further, drawing inspiration from the long-established classification framework in the pattern recognition literature, we provide definitions for the key notions of Bayes optimality and consistency in our extended vertex nomination framework, including a derivation of the Bayes optimal vertex nomination scheme. In addition, we prove that no universally consistent vertex nomination schemes exist. Illustrative examples are provided throughout.
Tasks	Information Retrieval
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05610v4
PDF	http://arxiv.org/pdf/1711.05610v4.pdf
PWC	https://paperswithcode.com/paper/on-consistent-vertex-nomination-schemes
Repo
Framework

EvaluationNet: Can Human Skill be Evaluated by Deep Networks?


Title	EvaluationNet: Can Human Skill be Evaluated by Deep Networks?
Authors	Seong Tae Kim, Yong Man Ro
Abstract	With the recent substantial growth of media such as YouTube, a considerable number of instructional videos covering a wide variety of tasks are available online. Therefore, online instructional videos have become a rich resource for humans to learn everyday skills. In order to improve the effectiveness of the learning with instructional video, observation and evaluation of the activity are required. However, it is difficult to observe and evaluate every activity steps by expert. In this study, a novel deep learning framework which targets human activity evaluation for learning from instructional video has been proposed. In order to deal with the inherent variability of activities, we propose to model activity as a structured process. First, action units are encoded from dense trajectories with LSTM network. The variable-length action unit features are then evaluated by a Siamese LSTM network. By the comparative experiments on public dataset, the effectiveness of the proposed method has been demonstrated.
Tasks
Published	2017-05-31
URL	http://arxiv.org/abs/1705.11077v1
PDF	http://arxiv.org/pdf/1705.11077v1.pdf
PWC	https://paperswithcode.com/paper/evaluationnet-can-human-skill-be-evaluated-by
Repo
Framework