July 28, 2019

2782 words 14 mins read

Paper Group ANR 425

A large comparison of feature-based approaches for buried target classification in forward-looking ground-penetrating radar. The Eigenoption-Critic Framework. Exploring Temporal Preservation Networks for Precise Temporal Action Localization. Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks. Convergence Rates for De …

A large comparison of feature-based approaches for buried target classification in forward-looking ground-penetrating radar


Title	A large comparison of feature-based approaches for buried target classification in forward-looking ground-penetrating radar
Authors	Joseph A. Camilo, Leslie M. Collins, Jordan M. Malof
Abstract	Forward-looking ground-penetrating radar (FLGPR) has recently been investigated as a remote sensing modality for buried target detection (e.g., landmines). In this context, raw FLGPR data is beamformed into images and then computerized algorithms are applied to automatically detect subsurface buried targets. Most existing algorithms are supervised, meaning they are trained to discriminate between labeled target and non-target imagery, usually based on features extracted from the imagery. A large number of features have been proposed for this purpose, however thus far it is unclear which are the most effective. The first goal of this work is to provide a comprehensive comparison of detection performance using existing features on a large collection of FLGPR data. Fusion of the decisions resulting from processing each feature is also considered. The second goal of this work is to investigate two modern feature learning approaches from the object recognition literature: the bag-of-visual-words and the Fisher vector for FLGPR processing. The results indicate that the new feature learning approaches outperform existing methods. Results also show that fusion between existing features and new features yields little additional performance improvements.
Tasks	Object Recognition
Published	2017-02-09
URL	http://arxiv.org/abs/1702.03000v1
PDF	http://arxiv.org/pdf/1702.03000v1.pdf
PWC	https://paperswithcode.com/paper/a-large-comparison-of-feature-based
Repo
Framework

The Eigenoption-Critic Framework


Title	The Eigenoption-Critic Framework
Authors	Miao Liu, Marlos C. Machado, Gerald Tesauro, Murray Campbell
Abstract	Eigenoptions (EOs) have been recently introduced as a promising idea for generating a diverse set of options through the graph Laplacian, having been shown to allow efficient exploration. Despite its initial promising results, a couple of issues in current algorithms limit its application, namely: (1) EO methods require two separate steps (eigenoption discovery and reward maximization) to learn a control policy, which can incur a significant amount of storage and computation; (2) EOs are only defined for problems with discrete state-spaces and; (3) it is not easy to take the environment’s reward function into consideration when discovering EOs. To addresses these issues, we introduce an algorithm termed eigenoption-critic (EOC) based on the Option-critic (OC) framework [Bacon17], a general hierarchical reinforcement learning (RL) algorithm that allows learning the intra-option policies simultaneously with the policy over options. We also propose a generalization of EOC to problems with continuous state-spaces through the Nystr"om approximation. EOC can also be seen as extending OC to nonstationary settings, where the discovered options are not tailored for a single task.
Tasks	Efficient Exploration, Hierarchical Reinforcement Learning
Published	2017-12-11
URL	http://arxiv.org/abs/1712.04065v1
PDF	http://arxiv.org/pdf/1712.04065v1.pdf
PWC	https://paperswithcode.com/paper/the-eigenoption-critic-framework
Repo
Framework

Exploring Temporal Preservation Networks for Precise Temporal Action Localization


Title	Exploring Temporal Preservation Networks for Precise Temporal Action Localization
Authors	Ke Yang, Peng Qiao, Dongsheng Li, Shaohe Lv, Yong Dou
Abstract	Temporal action localization is an important task of computer vision. Though a variety of methods have been proposed, it still remains an open question how to predict the temporal boundaries of action segments precisely. Most works use segment-level classifiers to select video segments pre-determined by action proposal or dense sliding windows. However, in order to achieve more precise action boundaries, a temporal localization system should make dense predictions at a fine granularity. A newly proposed work exploits Convolutional-Deconvolutional-Convolutional (CDC) filters to upsample the predictions of 3D ConvNets, making it possible to perform per-frame action predictions and achieving promising performance in terms of temporal action localization. However, CDC network loses temporal information partially due to the temporal downsampling operation. In this paper, we propose an elegant and powerful Temporal Preservation Convolutional (TPC) Network that equips 3D ConvNets with TPC filters. TPC network can fully preserve temporal resolution and downsample the spatial resolution simultaneously, enabling frame-level granularity action localization. TPC network can be trained in an end-to-end manner. Experiment results on public datasets show that TPC network achieves significant improvement on per-frame action prediction and competing results on segment-level temporal action localization.
Tasks	Action Localization, Temporal Action Localization, Temporal Localization
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03280v2
PDF	http://arxiv.org/pdf/1708.03280v2.pdf
PWC	https://paperswithcode.com/paper/exploring-temporal-preservation-networks-for
Repo
Framework

Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks


Title	Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks
Authors	Syed Shakib Sarwar, Priyadarshini Panda, Kaushik Roy
Abstract	Convolutional Neural Networks (CNN) are being increasingly used in computer vision for a wide range of classification and recognition problems. However, training these large networks demands high computational time and energy requirements; hence, their energy-efficient implementation is of great interest. In this work, we reduce the training complexity of CNNs by replacing certain weight kernels of a CNN with Gabor filters. The convolutional layers use the Gabor filters as fixed weight kernels, which extracts intrinsic features, with regular trainable weight kernels. This combination creates a balanced system that gives better training performance in terms of energy and time, compared to the standalone CNN (without any Gabor kernels), in exchange for tolerable accuracy degradation. We show that the accuracy degradation can be mitigated by partially training the Gabor kernels, for a small fraction of the total training cycles. We evaluated the proposed approach on 4 benchmark applications. Simple tasks like face detection and character recognition (MNIST and TiCH), were implemented using LeNet architecture. While a more complex task of object recognition (CIFAR10) was implemented on a state of the art deep CNN (Network in Network) architecture. The proposed approach yields 1.31-1.53x improvement in training energy in comparison to conventional CNN implementation. We also obtain improvement up to 1.4x in training time, up to 2.23x in storage requirements, and up to 2.2x in memory access energy. The accuracy degradation suffered by the approximate implementations is within 0-3% of the baseline.
Tasks	Face Detection, Object Recognition
Published	2017-05-12
URL	http://arxiv.org/abs/1705.04748v1
PDF	http://arxiv.org/pdf/1705.04748v1.pdf
PWC	https://paperswithcode.com/paper/gabor-filter-assisted-energy-efficient-fast
Repo
Framework

Convergence Rates for Deterministic and Stochastic Subgradient Methods Without Lipschitz Continuity


Title	Convergence Rates for Deterministic and Stochastic Subgradient Methods Without Lipschitz Continuity
Authors	Benjamin Grimmer
Abstract	We extend the classic convergence rate theory for subgradient methods to apply to non-Lipschitz functions. For the deterministic projected subgradient method, we present a global $O(1/\sqrt{T})$ convergence rate for any convex function which is locally Lipschitz around its minimizers. This approach is based on Shor’s classic subgradient analysis and implies generalizations of the standard convergence rates for gradient descent on functions with Lipschitz or H"older continuous gradients. Further, we show a $O(1/\sqrt{T})$ convergence rate for the stochastic projected subgradient method on convex functions with at most quadratic growth, which improves to $O(1/T)$ under either strong convexity or a weaker quadratic lower bound condition.
Tasks
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04104v3
PDF	http://arxiv.org/pdf/1712.04104v3.pdf
PWC	https://paperswithcode.com/paper/convergence-rates-for-deterministic-and
Repo
Framework

Block-diagonal Hessian-free Optimization for Training Neural Networks


Title	Block-diagonal Hessian-free Optimization for Training Neural Networks
Authors	Huishuai Zhang, Caiming Xiong, James Bradbury, Richard Socher
Abstract	Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are rarely applied to deep learning in practice because of high computational cost and the need for model-dependent algorithmic variations. We introduce a variant of the Hessian-free method that leverages a block-diagonal approximation of the generalized Gauss-Newton matrix. Our method computes the curvature approximation matrix only for pairs of parameters from the same layer or block of the neural network and performs conjugate gradient updates independently for each block. Experiments on deep autoencoders, deep convolutional networks, and multilayer LSTMs demonstrate better convergence and generalization compared to the original Hessian-free approach and the Adam method.
Tasks
Published	2017-12-20
URL	http://arxiv.org/abs/1712.07296v1
PDF	http://arxiv.org/pdf/1712.07296v1.pdf
PWC	https://paperswithcode.com/paper/block-diagonal-hessian-free-optimization-for
Repo
Framework

Characterizing the hyper-parameter space of LSTM language models for mixed context applications


Title	Characterizing the hyper-parameter space of LSTM language models for mixed context applications
Authors	Victor Akinwande, Sekou L. Remy
Abstract	Applying state of the art deep learning models to novel real world datasets gives a practical evaluation of the generalizability of these models. Of importance in this process is how sensitive the hyper parameters of such models are to novel datasets as this would affect the reproducibility of a model. We present work to characterize the hyper parameter space of an LSTM for language modeling on a code-mixed corpus. We observe that the evaluated model shows minimal sensitivity to our novel dataset bar a few hyper parameters.
Tasks	Language Modelling
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03199v1
PDF	http://arxiv.org/pdf/1712.03199v1.pdf
PWC	https://paperswithcode.com/paper/characterizing-the-hyper-parameter-space-of
Repo
Framework

SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation


Title	SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
Authors	Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, Le Song
Abstract	When function approximation is used, solving the Bellman optimality equation with stability guarantees has remained a major open problem in reinforcement learning for decades. The fundamental difficulty is that the Bellman operator may become an expansion in general, resulting in oscillating and even divergent behavior of popular algorithms like Q-learning. In this paper, we revisit the Bellman equation, and reformulate it into a novel primal-dual optimization problem using Nesterov’s smoothing technique and the Legendre-Fenchel transformation. We then develop a new algorithm, called Smoothed Bellman Error Embedding, to solve this optimization problem where any differentiable function class may be used. We provide what we believe to be the first convergence guarantee for general nonlinear function approximation, and analyze the algorithm’s sample complexity. Empirically, our algorithm compares favorably to state-of-the-art baselines in several benchmark control problems.
Tasks	Q-Learning
Published	2017-12-29
URL	http://arxiv.org/abs/1712.10285v4
PDF	http://arxiv.org/pdf/1712.10285v4.pdf
PWC	https://paperswithcode.com/paper/sbeed-convergent-reinforcement-learning-with
Repo
Framework

Structural Data Recognition with Graph Model Boosting


Title	Structural Data Recognition with Graph Model Boosting
Authors	Tomo Miyazaki, Shinichiro Omachi
Abstract	This paper presents a novel method for structural data recognition using a large number of graph models. In general, prevalent methods for structural data recognition have two shortcomings: 1) Only a single model is used to capture structural variation. 2) Naive recognition methods are used, such as the nearest neighbor method. In this paper, we propose strengthening the recognition performance of these models as well as their ability to capture structural variation. The proposed method constructs a large number of graph models and trains decision trees using the models. This paper makes two main contributions. The first is a novel graph model that can quickly perform calculations, which allows us to construct several models in a feasible amount of time. The second contribution is a novel approach to structural data recognition: graph model boosting. Comprehensive structural variations can be captured with a large number of graph models constructed in a boosting framework, and a sophisticated classifier can be formed by aggregating the decision trees. Consequently, we can carry out structural data recognition with powerful recognition capability in the face of comprehensive structural variation. The experiments shows that the proposed method achieves impressive results and outperforms existing methods on datasets of IAM graph database repository.
Tasks
Published	2017-03-08
URL	http://arxiv.org/abs/1703.02662v1
PDF	http://arxiv.org/pdf/1703.02662v1.pdf
PWC	https://paperswithcode.com/paper/structural-data-recognition-with-graph-model
Repo
Framework


Title	Blind Multiclass Ensemble Classification
Authors	Panagiotis A. Traganitis, Alba Pagès-Zamora, Georgios B. Giannakis
Abstract	The rising interest in pattern recognition and data analytics has spurred the development of innovative machine learning algorithms and tools. However, as each algorithm has its strengths and limitations, one is motivated to judiciously fuse multiple algorithms in order to find the “best” performing one, for a given dataset. Ensemble learning aims at such high-performance meta-algorithm, by combining the outputs from multiple algorithms. The present work introduces a blind scheme for learning from ensembles of classifiers, using a moment matching method that leverages joint tensor and matrix factorization. Blind refers to the combiner who has no knowledge of the ground-truth labels that each classifier has been trained on. A rigorous performance analysis is derived and the proposed scheme is evaluated on synthetic and real datasets.
Tasks
Published	2017-12-08
URL	http://arxiv.org/abs/1712.02903v2
PDF	http://arxiv.org/pdf/1712.02903v2.pdf
PWC	https://paperswithcode.com/paper/blind-multiclass-ensemble-classification
Repo
Framework

Dimensionality Reduction Ensembles


Title	Dimensionality Reduction Ensembles
Authors	Colleen M. Farrelly
Abstract	Ensemble learning has had many successes in supervised learning, but it has been rare in unsupervised learning and dimensionality reduction. This study explores dimensionality reduction ensembles, using principal component analysis and manifold learning techniques to capture linear, nonlinear, local, and global features in the original dataset. Dimensionality reduction ensembles are tested first on simulation data and then on two real medical datasets using random forest classifiers; results suggest the efficacy of this approach, with accuracies approaching that of the full dataset. Limitations include computational cost of some algorithms with strong performance, which may be ameliorated through distributed computing and the development of more efficient versions of these algorithms.
Tasks	Dimensionality Reduction
Published	2017-10-11
URL	http://arxiv.org/abs/1710.04484v1
PDF	http://arxiv.org/pdf/1710.04484v1.pdf
PWC	https://paperswithcode.com/paper/dimensionality-reduction-ensembles
Repo
Framework

RKL: a general, invariant Bayes solution for Neyman-Scott


Title	RKL: a general, invariant Bayes solution for Neyman-Scott
Authors	Michael Brand
Abstract	Neyman-Scott is a classic example of an estimation problem with a partially-consistent posterior, for which standard estimation methods tend to produce inconsistent results. Past attempts to create consistent estimators for Neyman-Scott have led to ad-hoc solutions, to estimators that do not satisfy representation invariance, to restrictions over the choice of prior and more. We present a simple construction for a general-purpose Bayes estimator, invariant to representation, which satisfies consistency on Neyman-Scott over any non-degenerate prior. We argue that the good attributes of the estimator are due to its intrinsic properties, and generalise beyond Neyman-Scott as well.
Tasks
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06366v1
PDF	http://arxiv.org/pdf/1707.06366v1.pdf
PWC	https://paperswithcode.com/paper/rkl-a-general-invariant-bayes-solution-for
Repo
Framework

High efficiency compression for object detection


Title	High efficiency compression for object detection
Authors	Hyomin Choi, Ivan V. Bajic
Abstract	Image and video compression has traditionally been tailored to human vision. However, modern applications such as visual analytics and surveillance rely on computers seeing and analyzing the images before (or instead of) humans. For these applications, it is important to adjust compression to computer vision. In this paper we present a bit allocation and rate control strategy that is tailored to object detection. Using the initial convolutional layers of a state-of-the-art object detector, we create an importance map that can guide bit allocation to areas that are important for object detection. The proposed method enables bit rate savings of 7% or more compared to default HEVC, at the equivalent object detection rate.
Tasks	Object Detection, Video Compression
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11151v2
PDF	http://arxiv.org/pdf/1710.11151v2.pdf
PWC	https://paperswithcode.com/paper/high-efficiency-compression-for-object
Repo
Framework

Fast Convolutional Sparse Coding in the Dual Domain


Title	Fast Convolutional Sparse Coding in the Dual Domain
Authors	Lama Affara, Bernard Ghanem, Peter Wonka
Abstract	Convolutional sparse coding (CSC) is an important building block of many computer vision applications ranging from image and video compression to deep learning. We present two contributions to the state of the art in CSC. First, we significantly speed up the computation by proposing a new optimization framework that tackles the problem in the dual domain. Second, we extend the original formulation to higher dimensions in order to process a wider range of inputs, such as RGB images and videos. Our results show up to 20 times speedup compared to current state-of-the-art CSC solvers.
Tasks	Video Compression
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09479v2
PDF	http://arxiv.org/pdf/1709.09479v2.pdf
PWC	https://paperswithcode.com/paper/fast-convolutional-sparse-coding-in-the-dual
Repo
Framework

Block-Matching Optical Flow for Dynamic Vision Sensor- Algorithm and FPGA Implementation


Title	Block-Matching Optical Flow for Dynamic Vision Sensor- Algorithm and FPGA Implementation
Authors	Min Liu, Tobi Delbruck
Abstract	Rapid and low power computation of optical flow (OF) is potentially useful in robotics. The dynamic vision sensor (DVS) event camera produces quick and sparse output, and has high dynamic range, but conventional OF algorithms are frame-based and cannot be directly used with event-based cameras. Previous DVS OF methods do not work well with dense textured input and are designed for implementation in logic circuits. This paper proposes a new block-matching based DVS OF algorithm which is inspired by motion estimation methods used for MPEG video compression. The algorithm was implemented both in software and on FPGA. For each event, it computes the motion direction as one of 9 directions. The speed of the motion is set by the sample interval. Results show that the Average Angular Error can be improved by 30% compared with previous methods. The OF can be calculated on FPGA with 50,MHz clock in 0.2,us per event (11 clock cycles), 20 times faster than a Java software implementation running on a desktop PC. Sample data is shown that the method works on scenes dominated by edges, sparse features, and dense texture.
Tasks	Motion Estimation, Optical Flow Estimation, Video Compression
Published	2017-06-16
URL	http://arxiv.org/abs/1706.05415v1
PDF	http://arxiv.org/pdf/1706.05415v1.pdf
PWC	https://paperswithcode.com/paper/block-matching-optical-flow-for-dynamic
Repo
Framework