January 31, 2020

2822 words 14 mins read

Paper Group AWR 409

VoIDext: Vocabulary and Patterns for Enhancing Interoperable Datasets with Virtual Links. Lookahead Optimizer: k steps forward, 1 step back. Loam_livox: A fast, robust, high-precision LiDAR odometry and mapping package for LiDARs of small FoV. Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data. Adversarial …

VoIDext: Vocabulary and Patterns for Enhancing Interoperable Datasets with Virtual Links


Title	VoIDext: Vocabulary and Patterns for Enhancing Interoperable Datasets with Virtual Links
Authors	Tarcisio Mendes de Farias, Kurt Stockinger, Christophe Dessimoz
Abstract	Semantic heterogeneity remains a problem when interoperating with data from sources of different scopes and knowledge domains. Causes for this challenge are context-specific requirements (i.e. no “one model fits all”), different data modelling decisions, domain-specific purposes, and technical constraints. Moreover, even if the problem of semantic heterogeneity among different RDF publishers and knowledge domains is solved, querying and accessing the data of distributed RDF datasets on the Web is not straightforward. This is because of the complex and fastidious process needed to understand how these datasets can be related or linked, and consequently, queried. To address this issue, we propose to extend the existing Vocabulary of Interlinked Datasets (VoID) by introducing new terms such as the Virtual Link Set concept and data model patterns. A virtual link is a connection between resources such as literals and IRIs (Internationalized Resource Identifier) with some commonality where each of these resources is from a different RDF dataset. The links are required in order to understand how to semantically relate datasets. In addition, we describe several benefits of using virtual links to improve interoperability between heterogenous and independent datasets. Finally, we exemplify and apply our approach to multiple world-wide used RDF datasets.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01950v3
PDF	https://arxiv.org/pdf/1906.01950v3.pdf
PWC	https://paperswithcode.com/paper/enhancing-interoperable-datasets-with-virtual
Repo	https://github.com/biosoda/voidext
Framework	none

Lookahead Optimizer: k steps forward, 1 step back


Title	Lookahead Optimizer: k steps forward, 1 step back
Authors	Michael R. Zhang, James Lucas, Geoffrey Hinton, Jimmy Ba
Abstract	The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate schemes, such as AdaGrad and Adam, and (2) accelerated schemes, such as heavy-ball and Nesterov momentum. In this paper, we propose a new optimization algorithm, Lookahead, that is orthogonal to these previous approaches and iteratively updates two sets of weights. Intuitively, the algorithm chooses a search direction by looking ahead at the sequence of fast weights generated by another optimizer. We show that Lookahead improves the learning stability and lowers the variance of its inner optimizer with negligible computation and memory cost. We empirically demonstrate Lookahead can significantly improve the performance of SGD and Adam, even with their default hyperparameter settings on ImageNet, CIFAR-10/100, neural machine translation, and Penn Treebank.
Tasks	Image Classification, Machine Translation, Stochastic Optimization
Published	2019-07-19
URL	https://arxiv.org/abs/1907.08610v2
PDF	https://arxiv.org/pdf/1907.08610v2.pdf
PWC	https://paperswithcode.com/paper/lookahead-optimizer-k-steps-forward-1-step
Repo	https://github.com/alphadl/lookahead.pytorch
Framework	pytorch

Loam_livox: A fast, robust, high-precision LiDAR odometry and mapping package for LiDARs of small FoV


Title	Loam_livox: A fast, robust, high-precision LiDAR odometry and mapping package for LiDARs of small FoV
Authors	Jiarong Lin, Fu Zhang
Abstract	LiDAR odometry and mapping (LOAM) has been playing an important role in autonomous vehicles, due to its ability to simultaneously localize the robot’s pose and build high-precision, high-resolution maps of the surrounding environment. This enables autonomous navigation and safe path planning of autonomous vehicles. In this paper, we present a robust, real-time LOAM algorithm for LiDARs with small FoV and irregular samplings. By taking effort on both front-end and back-end, we address several fundamental challenges arising from such LiDARs, and achieve better performance in both precision and efficiency compared to existing baselines. To share our findings and to make contributions to the community, we open source our codes on Github
Tasks	Autonomous Navigation, Autonomous Vehicles
Published	2019-09-15
URL	https://arxiv.org/abs/1909.06700v1
PDF	https://arxiv.org/pdf/1909.06700v1.pdf
PWC	https://paperswithcode.com/paper/loam_livox-a-fast-robust-high-precision-lidar
Repo	https://github.com/hku-mars/loam_livox
Framework	tf

Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data


Title	Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data
Authors	Felix M. Riese, Sina Keller
Abstract	Soil texture is important for many environmental processes. In this paper, we study the classification of soil texture based on hyperspectral data. We develop and implement three 1-dimensional (1D) convolutional neural networks (CNN): the LucasCNN, the LucasResNet which contains an identity block as residual network, and the LucasCoordConv with an additional coordinates layer. Furthermore, we modify two existing 1D CNN approaches for the presented classification task. The code of all five CNN approaches is available on GitHub (Riese, 2019). We evaluate the performance of the CNN approaches and compare them to a random forest classifier. Thereby, we rely on the freely available LUCAS topsoil dataset. The CNN approach with the least depth turns out to be the best performing classifier. The LucasCoordConv achieves the best performance regarding the average accuracy. In future work, we can further enhance the introduced LucasCNN, LucasResNet and LucasCoordConv and include additional variables of the rich LUCAS dataset.
Tasks	Texture Classification
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04846v3
PDF	http://arxiv.org/pdf/1901.04846v3.pdf
PWC	https://paperswithcode.com/paper/soil-texture-classification-with-1d
Repo	https://github.com/felixriese/CNN-SoilTextureClassification
Framework	tf

Adversarial Learning of a Sampler Based on an Unnormalized Distribution


Title	Adversarial Learning of a Sampler Based on an Unnormalized Distribution
Authors	Chunyuan Li, Ke Bai, Jianqiao Li, Guoyin Wang, Changyou Chen, Lawrence Carin
Abstract	We investigate adversarial learning in the case when only an unnormalized form of the density can be accessed, rather than samples. With insights so garnered, adversarial learning is extended to the case for which one has access to an unnormalized form u(x) of the target density function, but no samples. Further, new concepts in GAN regularization are developed, based on learning from samples or from u(x). The proposed method is compared to alternative approaches, with encouraging results demonstrated across a range of applications, including deep soft Q-learning.
Tasks	Q-Learning
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00612v1
PDF	http://arxiv.org/pdf/1901.00612v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-learning-of-a-sampler-based-on-an
Repo	https://github.com/ChunyuanLI/RAS
Framework	tf

CNN-based Lidar Point Cloud De-Noising in Adverse Weather


Title	CNN-based Lidar Point Cloud De-Noising in Adverse Weather
Authors	Robin Heinzler, Florian Piewak, Philipp Schindler, Wilhelm Stork
Abstract	Lidar sensors are frequently used in environment perception for autonomous vehicles and mobile robotics to complement camera, radar, and ultrasonic sensors. Adverse weather conditions are significantly impacting the performance of lidar-based scene understanding by causing undesired measurement points that in turn effect missing detections and false positives. In heavy rain or dense fog, water drops could be misinterpreted as objects in front of the vehicle which brings a mobile robot to a full stop. In this paper, we present the first CNN-based approach to understand and filter out such adverse weather effects in point cloud data. Using a large data set obtained in controlled weather environments, we demonstrate a significant performance improvement of our method over state-of-the-art involving geometric filtering. Data is available at https://github.com/rheinzler/PointCloudDeNoising.
Tasks	Autonomous Vehicles, Scene Understanding
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03874v2
PDF	https://arxiv.org/pdf/1912.03874v2.pdf
PWC	https://paperswithcode.com/paper/cnn-based-lidar-point-cloud-de-noising-in
Repo	https://github.com/rheinzler/PointCloudDeNoising
Framework	none

Bootstrapped Coordinate Search for Multidimensional Scaling


Title	Bootstrapped Coordinate Search for Multidimensional Scaling
Authors	Efthymios Tzinis
Abstract	In this work, a unified framework for gradient-free Multidimensional Scaling (MDS) based on Coordinate Search (CS) is proposed. This family of algorithms is an instance of General Pattern Search (GPS) methods which avoid the explicit computation of derivatives but instead evaluate the objective function while searching on coordinate steps of the embedding space. The backbone element of CSMDS framework is the corresponding probability matrix that correspond to how likely is each corresponding coordinate to be evaluated. We propose a Bootstrapped instance of CSMDS (BS CSMDS) which enhances the probability of the direction that decreases the most the objective function while also reducing the corresponding probability of all the other coordinates. BS CSMDS manages to avoid unnecessary function evaluations and result to significant speedup over other CSMDS alternatives while also obtaining the same error rate. Experiments on both synthetic and real data reveal that BS CSMDS performs consistently better than other CSMDS alternatives under various experimental setups.
Tasks
Published	2019-02-04
URL	http://arxiv.org/abs/1902.01482v1
PDF	http://arxiv.org/pdf/1902.01482v1.pdf
PWC	https://paperswithcode.com/paper/bootstrapped-coordinate-search-for
Repo	https://github.com/etzinis/bootstrapped_mds
Framework	none

Hybrid Cascaded Neural Network for Liver Lesion Segmentation


Title	Hybrid Cascaded Neural Network for Liver Lesion Segmentation
Authors	Raunak Dey, Yi Hong
Abstract	Automatic liver lesion segmentation is a challenging task while having a significant impact on assisting medical professionals in the designing of effective treatment and planning proper care. In this paper we propose a cascaded system that combines both 2D and 3D convolutional neural networks to effectively segment hepatic lesions. Our 2D network operates on a slice by slice basis to segment the liver and larger tumors, while we use a 3D network to detect small lesions that are often missed in a 2D segmentation design. We employ this algorithm on the LiTS challenge obtaining a Dice score per case of 68.1%, which performs the best among all non pre-trained models and the second best among published methods. We also perform two-fold cross-validation to reveal the over- and under-segmentation issues in the LiTS annotations.
Tasks	Lesion Segmentation
Published	2019-09-11
URL	https://arxiv.org/abs/1909.04797v3
PDF	https://arxiv.org/pdf/1909.04797v3.pdf
PWC	https://paperswithcode.com/paper/hybrid-cascaded-neural-network-for-liver
Repo	https://github.com/raun1/ISBI-2020-LITS_Hybrid_Comp_Net
Framework	tf

Video Representation Learning by Dense Predictive Coding


Title	Video Representation Learning by Dense Predictive Coding
Authors	Tengda Han, Weidi Xie, Andrew Zisserman
Abstract	The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for self-supervised representation learning on videos. This learns a dense encoding of spatio-temporal blocks by recurrently predicting future representations; Second, we propose a curriculum training scheme to predict further into the future with progressively less temporal context. This encourages the model to only encode slowly varying spatial-temporal signals, therefore leading to semantic representations; Third, we evaluate the approach by first training the DPC model on the Kinetics-400 dataset with self-supervised learning, and then finetuning the representation on a downstream task, i.e. action recognition. With single stream (RGB only), DPC pretrained representations achieve state-of-the-art self-supervised performance on both UCF101(75.7% top1 acc) and HMDB51(35.7% top1 acc), outperforming all previous learning methods by a significant margin, and approaching the performance of a baseline pre-trained on ImageNet.
Tasks	Representation Learning, Temporal Action Localization
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04656v3
PDF	https://arxiv.org/pdf/1909.04656v3.pdf
PWC	https://paperswithcode.com/paper/video-representation-learning-by-dense
Repo	https://github.com/TengdaHan/DPC
Framework	pytorch

Leveraging Outdoor Webcams for Local Descriptor Learning


Title	Leveraging Outdoor Webcams for Local Descriptor Learning
Authors	Milan Pultar, Dmytro Mishkin, Jiří Matas
Abstract	We present AMOS Patches, a large set of image cut-outs, intended primarily for the robustification of trainable local feature descriptors to illumination and appearance changes. Images contributing to AMOS Patches originate from the AMOS dataset of recordings from a large set of outdoor webcams. The semiautomatic method used to generate AMOS Patches is described. It includes camera selection, viewpoint clustering and patch selection. For training, we provide both the registered full source images as well as the patches. A new descriptor, trained on the AMOS Patches and 6Brown datasets, is introduced. It achieves state-of-the-art in matching under illumination changes on standard benchmarks.
Tasks
Published	2019-01-28
URL	http://arxiv.org/abs/1901.09780v1
PDF	http://arxiv.org/pdf/1901.09780v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-outdoor-webcams-for-local
Repo	https://github.com/pultarmi/AMOS_patches
Framework	none

DIODE: A Dense Indoor and Outdoor DEpth Dataset


Title	DIODE: A Dense Indoor and Outdoor DEpth Dataset
Authors	Igor Vasiljevic, Nick Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z. Dai, Andrea F. Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R. Walter, Gregory Shakhnarovich
Abstract	We introduce DIODE, a dataset that contains thousands of diverse high resolution color images with accurate, dense, long-range depth measurements. DIODE (Dense Indoor/Outdoor DEpth) is the first public dataset to include RGBD images of indoor and outdoor scenes obtained with one sensor suite. This is in contrast to existing datasets that focus on just one domain/scene type and employ different sensors, making generalization across domains difficult. The dataset is available for download at http://diode-dataset.org
Tasks
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00463v2
PDF	https://arxiv.org/pdf/1908.00463v2.pdf
PWC	https://paperswithcode.com/paper/diode-a-dense-indoor-and-outdoor-depth
Repo	https://github.com/diode-dataset/diode-devkit
Framework	pytorch

DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning


Title	DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning
Authors	Theo Jaunet, Romain Vuillemot, Christian Wolf
Abstract	We present DRLViz, a visual analytics interface to interpret the internal memory of an agent (e.g. a robot) trained using deep reinforcement learning. This memory is composed of large temporal vectors updated when the agent moves in an environment and is not trivial to understand. It is often referred to as a black box as only inputs (images) and outputs (actions) are intelligible for humans. Using DRLViz, experts are assisted to interpret using memory reduction interactions, to investigate parts of the memory role when errors have been made, and ultimately to improve the agent training process. We report on several examples of use of DRLViz, in the context of video games simulators (ViZDoom) for a navigation scenario with item gathering tasks. We also report on experts evaluation using DRLViz, and applicability of DRLViz to other scenarios and navigation problems beyond simulation games, as well as its contribution to black box models interpret-ability and explain-ability in the field of visual analytics.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02982v1
PDF	https://arxiv.org/pdf/1909.02982v1.pdf
PWC	https://paperswithcode.com/paper/drlviz-understanding-decisions-and-memory-in
Repo	https://github.com/sical/drlviz
Framework	none

Deep Neural Network Hyperparameter Optimization with Orthogonal Array Tuning


Title	Deep Neural Network Hyperparameter Optimization with Orthogonal Array Tuning
Authors	Xiang Zhang, Xiaocong Chen, Lina Yao, Chang Ge, Manqing Dong
Abstract	Deep learning algorithms have achieved excellent performance lately in a wide range of fields (e.g., computer version). However, a severe challenge faced by deep learning is the high dependency on hyper-parameters. The algorithm results may fluctuate dramatically under the different configuration of hyper-parameters. Addressing the above issue, this paper presents an efficient Orthogonal Array Tuning Method (OATM) for deep learning hyper-parameter tuning. We describe the OATM approach in five detailed steps and elaborate on it using two widely used deep neural network structures (Recurrent Neural Networks and Convolutional Neural Networks). The proposed method is compared to the state-of-the-art hyper-parameter tuning methods including manually (e.g., grid search and random search) and automatically (e.g., Bayesian Optimization) ones. The experiment results state that OATM can significantly save the tuning time compared to the state-of-the-art methods while preserving the satisfying performance. The codes are open in GitHub (https://github.com/xiangzhang1015/OATM)
Tasks	Hyperparameter Optimization
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13359v2
PDF	https://arxiv.org/pdf/1907.13359v2.pdf
PWC	https://paperswithcode.com/paper/deep-neural-network-hyperparameter
Repo	https://github.com/xiangzhang1015/OATM
Framework	tf

Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing


Title	Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing
Authors	Xiaoguang Tu, Jian Zhao, Mei Xie, Guodong Du, Hengsheng Zhang, Jianshu Li, Zheng Ma, Jiashi Feng
Abstract	Face anti-spoofing (a.k.a presentation attack detection) has drawn growing attention due to the high-security demand in face authentication systems. Existing CNN-based approaches usually well recognize the spoofing faces when training and testing spoofing samples display similar patterns, but their performance would drop drastically on testing spoofing faces of unseen scenes. In this paper, we try to boost the generalizability and applicability of these methods by designing a CNN model with two major novelties. First, we propose a simple yet effective Total Pairwise Confusion (TPC) loss for CNN training, which enhances the generalizability of the learned Presentation Attack (PA) representations. Secondly, we incorporate a Fast Domain Adaptation (FDA) component into the CNN model to alleviate negative effects brought by domain changes. Besides, our proposed model, which is named Generalizable Face Authentication CNN (GFA-CNN), works in a multi-task manner, performing face anti-spoofing and face recognition simultaneously. Experimental results show that GFA-CNN outperforms previous face anti-spoofing approaches and also well preserves the identity information of input face images.
Tasks	Domain Adaptation, Face Anti-Spoofing, Face Recognition
Published	2019-01-17
URL	http://arxiv.org/abs/1901.05602v1
PDF	http://arxiv.org/pdf/1901.05602v1.pdf
PWC	https://paperswithcode.com/paper/learning-generalizable-and-identity
Repo	https://github.com/XgTu/GFA-CNN
Framework	tf

A novel approach to multivariate redundancy and synergy


Title	A novel approach to multivariate redundancy and synergy
Authors	Artemy Kolchinsky
Abstract	Consider a situation in which a set of $n$ “source” random variables $X_{1},\dots,X_{n}$ have information about some “target” random variable $Y$. For example, in neuroscience $Y$ might represent the state of an external stimulus and $X_{1},\dots,X_{n}$ the activity of $n$ different brain regions. Recent work in information theory has considered how to decompose the information that the sources $X_{1},\dots,X_{n}$ provide about the target $Y$ into separate terms such as (1) the “redundant information” that is shared among all of sources, (2) the “unique information” that is provided only by a single source, (3) the “synergistic information” that is provided by all sources only when considered jointly, and (4) the “union information” that is provided by at least one source. We propose a novel framework deriving such a decomposition that can be applied to any number of sources. Our measures are motivated in three distinct ways: via a formal analogy to intersection and union operators in set theory, via a decision-theoretic operationalization based on Blackwell’s theorem, and via an axiomatic derivation. A key aspect of our approach is that we relax the assumption that measures of redundancy and union information should be related by the inclusion-exclusion principle. We discuss relations to previous proposals as well as possible generalizations.
Tasks
Published	2019-08-23
URL	https://arxiv.org/abs/1908.08642v3
PDF	https://arxiv.org/pdf/1908.08642v3.pdf
PWC	https://paperswithcode.com/paper/a-novel-approach-to-multivariate-redundancy
Repo	https://github.com/artemyk/redundancy
Framework	none