May 7, 2019

3373 words 16 mins read

Paper Group ANR 151

Latest Datasets and Technologies Presented in the Workshop on Grasping and Manipulation Datasets. Partial Recovery Bounds for the Sparse Stochastic Block Model. Image segmentation of cross-country scenes captured in IR spectrum. Which techniques does your application use?: An information extraction framework for scientific articles. Noisy Activatio …

Latest Datasets and Technologies Presented in the Workshop on Grasping and Manipulation Datasets


Title	Latest Datasets and Technologies Presented in the Workshop on Grasping and Manipulation Datasets
Authors	Matteo Bianchi, Jeannette Bohg, Yu Sun
Abstract	This paper reports the activities and outcomes in the Workshop on Grasping and Manipulation Datasets that was organized under the International Conference on Robotics and Automation (ICRA) 2016. The half day workshop was packed with nine invited talks, 12 interactive presentations, and one panel discussion with ten panelists. This paper summarizes all the talks and presentations and recaps what has been discussed in the panels session. This summary servers as a review of recent developments in data collection in grasping and manipulation. Many of the presentations describe ongoing efforts or explorations that could be achieved and fully available in a year or two. The panel discussion not only commented on the current approaches, but also indicates new directions and focuses. The workshop clearly displayed the importance of quality datasets in robotics and robotic grasping and manipulation field. Hopefully the workshop could motivate larger efforts to create big datasets that are comparable with big datasets in other communities such as computer vision.
Tasks	Robotic Grasping
Published	2016-09-08
URL	http://arxiv.org/abs/1609.02531v1
PDF	http://arxiv.org/pdf/1609.02531v1.pdf
PWC	https://paperswithcode.com/paper/latest-datasets-and-technologies-presented-in
Repo
Framework

Partial Recovery Bounds for the Sparse Stochastic Block Model


Title	Partial Recovery Bounds for the Sparse Stochastic Block Model
Authors	Jonathan Scarlett, Volkan Cevher
Abstract	In this paper, we study the information-theoretic limits of community detection in the symmetric two-community stochastic block model, with intra-community and inter-community edge probabilities $\frac{a}{n}$ and $\frac{b}{n}$ respectively. We consider the sparse setting, in which $a$ and $b$ do not scale with $n$, and provide upper and lower bounds on the proportion of community labels recovered on average. We provide a numerical example for which the bounds are near-matching for moderate values of $a - b$, and matching in the limit as $a-b$ grows large.
Tasks	Community Detection
Published	2016-02-02
URL	http://arxiv.org/abs/1602.00877v2
PDF	http://arxiv.org/pdf/1602.00877v2.pdf
PWC	https://paperswithcode.com/paper/partial-recovery-bounds-for-the-sparse
Repo
Framework

Image segmentation of cross-country scenes captured in IR spectrum


Title	Image segmentation of cross-country scenes captured in IR spectrum
Authors	Artem Lenskiy
Abstract	Computer vision has become a major source of information for autonomous navigation of robots of various types, self-driving cars, military robots and mars/lunar rovers are some examples. Nevertheless, the majority of methods focus on analysing images captured in visible spectrum. In this manuscript we elaborate on the problem of segmenting cross-country scenes captured in IR spectrum. For this purpose we proposed employing salient features. Salient features are robust to variations in scale, brightness and view angle. We suggest the Speeded-Up Robust Features as a basis for our salient features for a number of reasons discussed in the paper. We also provide a comparison of two SURF implementations. The SURF features are extracted from images of different terrain types. For every feature we estimate a terrain class membership function. The membership values are obtained by means of either the multi-layer perceptron or nearest neighbours. The features’ class membership values and their spatial positions are then applied to estimate class membership values for all pixels in the image. To decrease the effect of segmentation blinking that is caused by rapid switching between different terrain types and to speed up segmentation, we are tracking camera position and predict features’ positions. The comparison of the multi-layer perception and the nearest neighbour classifiers is presented in the paper. The error rate of the terrain segmentation using the nearest neighbours obtained on the testing set is 16.6+-9.17%.
Tasks	Autonomous Navigation, Self-Driving Cars, Semantic Segmentation
Published	2016-04-08
URL	http://arxiv.org/abs/1604.02469v1
PDF	http://arxiv.org/pdf/1604.02469v1.pdf
PWC	https://paperswithcode.com/paper/image-segmentation-of-cross-country-scenes
Repo
Framework

Which techniques does your application use?: An information extraction framework for scientific articles


Title	Which techniques does your application use?: An information extraction framework for scientific articles
Authors	Soham Dan, Sanyam Agarwal, Mayank Singh, Pawan Goyal, Animesh Mukherjee
Abstract	Every field of research consists of multiple application areas with various techniques routinely used to solve problems in these wide range of application areas. With the exponential growth in research volumes, it has become difficult to keep track of the ever-growing number of application areas as well as the corresponding problem solving techniques. In this paper, we consider the computational linguistics domain and present a novel information extraction system that automatically constructs a pool of all application areas in this domain and appropriately links them with corresponding problem solving techniques. Further, we categorize individual research articles based on their application area and the techniques proposed/used in the article. k-gram based discounting method along with handwritten rules and bootstrapped pattern learning is employed to extract application areas. Subsequently, a language modeling approach is proposed to characterize each article based on its application area. Similarly, regular expressions and high-scoring noun phrases are used for the extraction of the problem solving techniques. We propose a greedy approach to characterize each article based on the techniques. Towards the end, we present a table representing the most frequent techniques adopted for a particular application area. Finally, we propose three use cases presenting an extensive temporal analysis of the usage of techniques and application areas.
Tasks	Language Modelling
Published	2016-08-23
URL	http://arxiv.org/abs/1608.06386v1
PDF	http://arxiv.org/pdf/1608.06386v1.pdf
PWC	https://paperswithcode.com/paper/which-techniques-does-your-application-use-an
Repo
Framework

Noisy Activation Functions


Title	Noisy Activation Functions
Authors	Caglar Gulcehre, Marcin Moczulski, Misha Denil, Yoshua Bengio
Abstract	Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only). Gating mechanisms that use softly saturating activation functions to emulate the discrete switching of digital logic circuits are good examples of this. We propose to exploit the injection of appropriate noise so that the gradients may flow easily, even if the noiseless application of the activation function would yield zero gradient. Large noise will dominate the noise-free gradient and allow stochastic gradient descent toexplore more. By adding noise only to the problematic parts of the activation function, we allow the optimization procedure to explore the boundary between the degenerate (saturating) and the well-behaved parts of the activation function. We also establish connections to simulated annealing, when the amount of noise is annealed down, making it easier to optimize hard objective functions. We find experimentally that replacing such saturating activation functions by noisy variants helps training in many contexts, yielding state-of-the-art or competitive results on different datasets and task, especially when training seems to be the most difficult, e.g., when curriculum learning is necessary to obtain good results.
Tasks
Published	2016-03-01
URL	http://arxiv.org/abs/1603.00391v3
PDF	http://arxiv.org/pdf/1603.00391v3.pdf
PWC	https://paperswithcode.com/paper/noisy-activation-functions
Repo
Framework


Title	Autonomous navigation for low-altitude UAVs in urban areas
Authors	Thomas Castelli, Aidean Sharghi, Don Harper, Alain Tremeau, Mubarak Shah
Abstract	In recent years, consumer Unmanned Aerial Vehicles have become very popular, everyone can buy and fly a drone without previous experience, which raises concern in regards to regulations and public safety. In this paper, we present a novel approach towards enabling safe operation of such vehicles in urban areas. Our method uses geodetically accurate dataset images with Geographical Information System (GIS) data of road networks and buildings provided by Google Maps, to compute a weighted A* shortest path from start to end locations of a mission. Weights represent the potential risk of injuries for individuals in all categories of land-use, i.e. flying over buildings is considered safer than above roads. We enable safe UAV operation in regards to 1- land-use by computing a static global path dependent on environmental structures, and 2- avoiding flying over moving objects such as cars and pedestrians by dynamically optimizing the path locally during the flight. As all input sources are first geo-registered, pixels and GPS coordinates are equivalent, it therefore allows us to generate an automated and user-friendly mission with GPS waypoints readable by consumer drones’ autopilots. We simulated 54 missions and show significant improvement in maximizing UAV’s standoff distance to moving objects with a quantified safety parameter over 40 times better than the naive straight line navigation.
Tasks	Autonomous Navigation
Published	2016-02-25
URL	http://arxiv.org/abs/1602.08141v1
PDF	http://arxiv.org/pdf/1602.08141v1.pdf
PWC	https://paperswithcode.com/paper/autonomous-navigation-for-low-altitude-uavs
Repo
Framework

Excisive Hierarchical Clustering Methods for Network Data


Title	Excisive Hierarchical Clustering Methods for Network Data
Authors	Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra
Abstract	We introduce two practical properties of hierarchical clustering methods for (possibly asymmetric) network data: excisiveness and linear scale preservation. The latter enforces imperviousness to change in units of measure whereas the former ensures local consistency of the clustering outcome. Algorithmically, excisiveness implies that we can reduce computational complexity by only clustering a data subset of interest while theoretically guaranteeing that the same hierarchical outcome would be observed when clustering the whole dataset. Moreover, we introduce the concept of representability, i.e. a generative model for describing clustering methods through the specification of their action on a collection of networks. We further show that, within a rich set of admissible methods, requiring representability is equivalent to requiring both excisiveness and linear scale preservation. Leveraging this equivalence, we show that all excisive and linear scale preserving methods can be factored into two steps: a transformation of the weights in the input network followed by the application of a canonical clustering method. Furthermore, their factorization can be used to show stability of excisive and linear scale preserving methods in the sense that a bounded perturbation in the input network entails a bounded perturbation in the clustering output.
Tasks
Published	2016-07-21
URL	http://arxiv.org/abs/1607.06339v1
PDF	http://arxiv.org/pdf/1607.06339v1.pdf
PWC	https://paperswithcode.com/paper/excisive-hierarchical-clustering-methods-for
Repo
Framework

Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network


Title	Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network
Authors	Hanming Zhang, Liang Li, Kai Qiao, Linyuan Wang, Bin Yan, Lei Li, Guoen Hu
Abstract	Limited angle problem is a challenging issue in x-ray computed tomography (CT) field. Iterative reconstruction methods that utilize the additional prior can suppress artifacts and improve image quality, but unfortunately require increased computation time. An interesting way is to restrain the artifacts in the images reconstructed from the practical filtered back projection (FBP) method. Frikel and Quinto have proved that the streak artifacts in FBP results could be characterized. It indicates that the artifacts created by FBP method have specific and similar characteristics in a stationary limited-angle scanning configuration. Based on this understanding, this work aims at developing a method to extract and suppress specific artifacts of FBP reconstructions for limited-angle tomography. A data-driven learning-based method is proposed based on a deep convolutional neural network. An end-to-end mapping between the FBP and artifact-free images is learned and the implicit features involving artifacts will be extracted and suppressed via nonlinear mapping. The qualitative and quantitative evaluations of experimental results indicate that the proposed method show a stable and prospective performance on artifacts reduction and detail recovery for limited angle tomography. The presented strategy provides a simple and efficient approach for improving image quality of the reconstruction results from limited projection data.
Tasks	Computed Tomography (CT)
Published	2016-07-29
URL	http://arxiv.org/abs/1607.08707v1
PDF	http://arxiv.org/pdf/1607.08707v1.pdf
PWC	https://paperswithcode.com/paper/image-prediction-for-limited-angle-tomography
Repo
Framework

Compositional Sentence Representation from Character within Large Context Text


Title	Compositional Sentence Representation from Character within Large Context Text
Authors	Geonmin Kim, Hwaran Lee, Jisu Choi, Soo-young Lee
Abstract	This paper describes a Hierarchical Composition Recurrent Network (HCRN) consisting of a 3-level hierarchy of compositional models: character, word and sentence. This model is designed to overcome two problems of representing a sentence on the basis of a constituent word sequence. The first is a data-sparsity problem in word embedding, and the other is a no usage of inter-sentence dependency. In the HCRN, word representations are built from characters, thus resolving the data-sparsity problem, and inter-sentence dependency is embedded into sentence representation at the level of sentence composition. We adopt a hierarchy-wise learning scheme in order to alleviate the optimization difficulties of learning deep hierarchical recurrent network in end-to-end fashion. The HCRN was quantitatively and qualitatively evaluated on a dialogue act classification task. Especially, sentence representations with an inter-sentence dependency are able to capture both implicit and explicit semantics of sentence, significantly improving performance. In the end, the HCRN achieved state-of-the-art performance with a test error rate of 22.7% for dialogue act classification on the SWBD-DAMSL database.
Tasks	Dialogue Act Classification
Published	2016-05-02
URL	http://arxiv.org/abs/1605.00482v3
PDF	http://arxiv.org/pdf/1605.00482v3.pdf
PWC	https://paperswithcode.com/paper/compositional-sentence-representation-from
Repo
Framework

Improved prediction accuracy for disease risk mapping using Gaussian Process stacked generalisation


Title	Improved prediction accuracy for disease risk mapping using Gaussian Process stacked generalisation
Authors	Samir Bhatt, Ewan Cameron, Seth R Flaxman, Daniel J Weiss, David L Smith, Peter W Gething
Abstract	Maps of infectious disease—charting spatial variations in the force of infection, degree of endemicity, and the burden on human health—provide an essential evidence base to support planning towards global health targets. Contemporary disease mapping efforts have embraced statistical modelling approaches to properly acknowledge uncertainties in both the available measurements and their spatial interpolation. The most common such approach is that of Gaussian process regression, a mathematical framework comprised of two components: a mean function harnessing the predictive power of multiple independent variables, and a covariance function yielding spatio-temporal shrinkage against residual variation from the mean. Though many techniques have been developed to improve the flexibility and fitting of the covariance function, models for the mean function have typically been restricted to simple linear terms. For infectious diseases, known to be driven by complex interactions between environmental and socio-economic factors, improved modelling of the mean function can greatly boost predictive power. Here we present an ensemble approach based on stacked generalisation that allows for multiple, non-linear algorithmic mean functions to be jointly embedded within the Gaussian process framework. We apply this method to mapping Plasmodium falciparum prevalence data in Sub-Saharan Africa and show that the generalised ensemble approach markedly out-performs any individual method.
Tasks
Published	2016-12-10
URL	http://arxiv.org/abs/1612.03278v1
PDF	http://arxiv.org/pdf/1612.03278v1.pdf
PWC	https://paperswithcode.com/paper/improved-prediction-accuracy-for-disease-risk
Repo
Framework

RIDS: Robust Identification of Sparse Gene Regulatory Networks from Perturbation Experiments


Title	RIDS: Robust Identification of Sparse Gene Regulatory Networks from Perturbation Experiments
Authors	Hoi-To Wai, Anna Scaglione, Uzi Harush, Baruch Barzel, Amir Leshem
Abstract	Reconstructing the causal network in a complex dynamical system plays a crucial role in many applications, from sub-cellular biology to economic systems. Here we focus on inferring gene regulation networks (GRNs) from perturbation or gene deletion experiments. Despite their scientific merit, such perturbation experiments are not often used for such inference due to their costly experimental procedure, requiring significant resources to complete the measurement of every single experiment. To overcome this challenge, we develop the Robust IDentification of Sparse networks (RIDS) method that reconstructs the GRN from a small number of perturbation experiments. Our method uses the gene expression data observed in each experiment and translates that into a steady state condition of the system’s nonlinear interaction dynamics. Applying a sparse optimization criterion, we are able to extract the parameters of the underlying weighted network, even from very few experiments. In fact, we demonstrate analytically that, under certain conditions, the GRN can be perfectly reconstructed using $K = \Omega (d_{max})$ perturbation experiments, where $d_{max}$ is the maximum in-degree of the GRN, a small value for realistic sparse networks, indicating that RIDS can achieve high performance with a scalable number of experiments. We test our method on both synthetic and experimental data extracted from the DREAM5 network inference challenge. We show that the RIDS achieves superior performance compared to the state-of-the-art methods, while requiring as few as ~60% less experimental data. Moreover, as opposed to almost all competing methods, RIDS allows us to infer the directionality of the GRN links, allowing us to infer empirical GRNs, without relying on the commonly provided list of transcription factors.
Tasks
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06565v1
PDF	http://arxiv.org/pdf/1612.06565v1.pdf
PWC	https://paperswithcode.com/paper/rids-robust-identification-of-sparse-gene
Repo
Framework

Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association


Title	Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association
Authors	Bing Wang, Li Wang, Bing Shuai, Zhen Zuo, Ting Liu, Kap Luk Chan, Gang Wang
Abstract	In this paper, we study the challenging problem of multi-object tracking in a complex scene captured by a single camera. Different from the existing tracklet association-based tracking methods, we propose a novel and efficient way to obtain discriminative appearance-based tracklet affinity models. Our proposed method jointly learns the convolutional neural networks (CNNs) and temporally constrained metrics. In our method, a Siamese convolutional neural network (CNN) is first pre-trained on the auxiliary data. Then the Siamese CNN and temporally constrained metrics are jointly learned online to construct the appearance-based tracklet affinity models. The proposed method can jointly learn the hierarchical deep features and temporally constrained segment-wise metrics under a unified framework. For reliable association between tracklets, a novel loss function incorporating temporally constrained multi-task learning mechanism is proposed. By employing the proposed method, tracklet association can be accomplished even in challenging situations. Moreover, a new dataset with 40 fully annotated sequences is created to facilitate the tracking evaluation. Experimental results on five public datasets and the new large-scale dataset show that our method outperforms several state-of-the-art approaches in multi-object tracking.
Tasks	Multi-Object Tracking, Multi-Task Learning, Object Tracking
Published	2016-05-15
URL	http://arxiv.org/abs/1605.04502v2
PDF	http://arxiv.org/pdf/1605.04502v2.pdf
PWC	https://paperswithcode.com/paper/joint-learning-of-siamese-cnns-and-temporally
Repo
Framework

Video Ladder Networks


Title	Video Ladder Networks
Authors	Francesco Cricri, Xingyang Ni, Mikko Honkala, Emre Aksu, Moncef Gabbouj
Abstract	We present the Video Ladder Network (VLN) for efficiently generating future video frames. VLN is a neural encoder-decoder model augmented at all layers by both recurrent and feedforward lateral connections. At each layer, these connections form a lateral recurrent residual block, where the feedforward connection represents a skip connection and the recurrent connection represents the residual. Thanks to the recurrent connections, the decoder can exploit temporal summaries generated from all layers of the encoder. This way, the top layer is relieved from the pressure of modeling lower-level spatial and temporal details. Furthermore, we extend the basic version of VLN to incorporate ResNet-style residual blocks in the encoder and decoder, which help improving the prediction results. VLN is trained in self-supervised regime on the Moving MNIST dataset, achieving competitive results while having very simple structure and providing fast inference.
Tasks
Published	2016-12-06
URL	http://arxiv.org/abs/1612.01756v3
PDF	http://arxiv.org/pdf/1612.01756v3.pdf
PWC	https://paperswithcode.com/paper/video-ladder-networks
Repo
Framework

Efficient Robust Mean Value Calculation of 1D Features


Title	Efficient Robust Mean Value Calculation of 1D Features
Authors	Erik Jonsson, Michael Felsberg
Abstract	A robust mean value is often a good alternative to the standard mean value when dealing with data containing many outliers. An efficient method for samples of one-dimensional features and the truncated quadratic error norm is presented and compared to the method of channel averaging (soft histograms).
Tasks
Published	2016-01-29
URL	http://arxiv.org/abs/1601.08003v1
PDF	http://arxiv.org/pdf/1601.08003v1.pdf
PWC	https://paperswithcode.com/paper/efficient-robust-mean-value-calculation-of-1d
Repo
Framework

Constrained Low-Rank Learning Using Least Squares-Based Regularization


Title	Constrained Low-Rank Learning Using Least Squares-Based Regularization
Authors	Ping Li, Jun Yu, Meng Wang, Luming Zhang, Deng Cai, Xuelong Li
Abstract	Low-rank learning has attracted much attention recently due to its efficacy in a rich variety of real-world tasks, e.g., subspace segmentation and image categorization. Most low-rank methods are incapable of capturing low-dimensional subspace for supervised learning tasks, e.g., classification and regression. This paper aims to learn both the discriminant low-rank representation (LRR) and the robust projecting subspace in a supervised manner. To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization. Naturally, the data label structure tends to resemble that of the corresponding low-dimensional representation, which is derived from the robust subspace projection of clean data by low-rank learning. Moreover, the low-dimensional representation of original data can be paired with some informative structure by imposing an appropriate constraint, e.g., Laplacian regularizer. Therefore, we propose a novel constrained LRR method. The objective function is formulated as a constrained nuclear norm minimization problem, which can be solved by the inexact augmented Lagrange multiplier algorithm. Extensive experiments on image classification, human pose estimation, and robust face recovery have confirmed the superiority of our method.
Tasks	Image Categorization, Image Classification, Pose Estimation
Published	2016-11-15
URL	http://arxiv.org/abs/1611.04870v1
PDF	http://arxiv.org/pdf/1611.04870v1.pdf
PWC	https://paperswithcode.com/paper/constrained-low-rank-learning-using-least
Repo
Framework