April 2, 2020

2834 words 14 mins read

Paper Group ANR 351

A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks. Autonomous Control of a Line Follower Robot Using a Q-Learning Controller. Deep Learning for Classifying Food Waste. VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge. Very simple stat …

A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks


Title	A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks
Authors	C. Qiu, M. Schmitt, C. Geiss, T. K. Chen, X. X. Zhu
Abstract	Human settlement extent (HSE) information is a valuable indicator of world-wide urbanization as well as the resulting human pressure on the natural environment. Therefore, mapping HSE is critical for various environmental issues at local, regional, and even global scales. This paper presents a deep-learning-based framework to automatically map HSE from multi-spectral Sentinel-2 data using regionally available geo-products as training labels. A straightforward, simple, yet effective fully convolutional network-based architecture, Sen2HSE, is implemented as an example for semantic segmentation within the framework. The framework is validated against both manually labelled checking points distributed evenly over the test areas, and the OpenStreetMap building layer. The HSE mapping results were extensively compared to several baseline products in order to thoroughly evaluate the effectiveness of the proposed HSE mapping framework. The HSE mapping power is consistently demonstrated over 10 representative areas across the world. We also present one regional-scale and one country-wide HSE mapping example from our framework to show the potential for upscaling. The results of this study contribute to the generalization of the applicability of CNN-based approaches for large-scale urban mapping to cases where no up-to-date and accurate ground truth is available, as well as the subsequent monitor of global urbanization.
Tasks	Semantic Segmentation
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11935v1
PDF	https://arxiv.org/pdf/2001.11935v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-large-scale-mapping-of-human
Repo
Framework

Autonomous Control of a Line Follower Robot Using a Q-Learning Controller


Title	Autonomous Control of a Line Follower Robot Using a Q-Learning Controller
Authors	Sepehr Saadatmand, Sima Azizi, Mohammadamir Kavousi, Donald Wunsch
Abstract	In this paper, a MIMO simulated annealing SA based Q learning method is proposed to control a line follower robot. The conventional controller for these types of robots is the proportional P controller. Considering the unknown mechanical characteristics of the robot and uncertainties such as friction and slippery surfaces, system modeling and controller designing can be extremely challenging. The mathematical modeling for the robot is presented in this paper, and a simulator is designed based on this model. The basic Q learning methods are based pure exploitation and the epsilon-greedy methods, which help exploration, can harm the controller performance after learning completion by exploring nonoptimal actions. The simulated annealing based Q learning method tackles this drawback by decreasing the exploration rate when the learning increases. The simulation and experimental results are provided to evaluate the effectiveness of the proposed controller.
Tasks	Q-Learning
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08841v1
PDF	https://arxiv.org/pdf/2001.08841v1.pdf
PWC	https://paperswithcode.com/paper/autonomous-control-of-a-line-follower-robot
Repo
Framework

Deep Learning for Classifying Food Waste


Title	Deep Learning for Classifying Food Waste
Authors	Amin Mazloumian, Matthias Rosenthal, Hans Gelke
Abstract	One third of food produced in the world for human consumption – approximately 1.3 billion tons – is lost or wasted every year. By classifying food waste of individual consumers and raising awareness of the measures, avoidable food waste can be significantly reduced. In this research, we use deep learning to classify food waste in half a million images captured by cameras installed on top of food waste bins. We specifically designed a deep neural network that classifies food waste for every time food waste is thrown in the waste bins. Our method presents how deep learning networks can be tailored to best learn from available training data.
Tasks
Published	2020-02-06
URL	https://arxiv.org/abs/2002.03786v1
PDF	https://arxiv.org/pdf/2002.03786v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-classifying-food-waste
Repo
Framework

VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge


Title	VESR-Net: The Winning Solution to Youku Video Enhancement and Super-Resolution Challenge
Authors	Jiale Chen, Xu Tan, Chaowei Shan, Sen Liu, Zhibo Chen
Abstract	This paper introduces VESR-Net, a method for video enhancement and super-resolution (VESR). We design a separate non-local module to explore the relations among video frames and fuse video frames efficiently, and a channel attention residual block to capture the relations among feature maps for video frame reconstruction in VESR-Net. We conduct experiments to analyze the effectiveness of these designs in VESR-Net, which demonstrates the advantages of VESR-Net over previous state-of-the-art VESR methods. It is worth to mention that among more than thousands of participants for Youku video enhancement and super-resolution (Youku-VESR) challenge, our proposed VESR-Net beat other competitive methods and ranked the first place.
Tasks	Super-Resolution
Published	2020-03-04
URL	https://arxiv.org/abs/2003.02115v1
PDF	https://arxiv.org/pdf/2003.02115v1.pdf
PWC	https://paperswithcode.com/paper/vesr-net-the-winning-solution-to-youku-video
Repo
Framework

Very simple statistical evidence that AlphaGo has exceeded human limits in playing GO game


Title	Very simple statistical evidence that AlphaGo has exceeded human limits in playing GO game
Authors	Okyu Kwon
Abstract	Deep learning technology is making great progress in solving the challenging problems of artificial intelligence, hence machine learning based on artificial neural networks is in the spotlight again. In some areas, artificial intelligence based on deep learning is beyond human capabilities. It seemed extremely difficult for a machine to beat a human in a Go game, but AlphaGo has shown to beat a professional player in the game. By looking at the statistical distribution of the distance in which the Go stones are laid in succession, we find a clear trace that Alphago has surpassed human abilities. The AlphaGo than professional players and professional players than ordinary players shows the laying of stones in the distance becomes more frequent. In addition, AlphaGo shows a much more pronounced difference than that of ordinary players and professional players.
Tasks
Published	2020-02-25
URL	https://arxiv.org/abs/2002.11107v1
PDF	https://arxiv.org/pdf/2002.11107v1.pdf
PWC	https://paperswithcode.com/paper/very-simple-statistical-evidence-that-alphago
Repo
Framework

Batch norm with entropic regularization turns deterministic autoencoders into generative models


Title	Batch norm with entropic regularization turns deterministic autoencoders into generative models
Authors	Amur Ghose, Abdullah Rashwan, Pascal Poupart
Abstract	The variational autoencoder is a well defined deep generative model that utilizes an encoder-decoder framework where an encoding neural network outputs a non-deterministic code for reconstructing an input. The encoder achieves this by sampling from a distribution for every input, instead of outputting a deterministic code per input. The great advantage of this process is that it allows the use of the network as a generative model for sampling from the data distribution beyond provided samples for training. We show in this work that utilizing batch normalization as a source for non-determinism suffices to turn deterministic autoencoders into generative models on par with variational ones, so long as we add a suitable entropic regularization to the training objective.
Tasks
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10631v1
PDF	https://arxiv.org/pdf/2002.10631v1.pdf
PWC	https://paperswithcode.com/paper/batch-norm-with-entropic-regularization-turns
Repo
Framework

Memory Organization for Energy-Efficient Learning and Inference in Digital Neuromorphic Accelerators


Title	Memory Organization for Energy-Efficient Learning and Inference in Digital Neuromorphic Accelerators
Authors	Clemens JS Schaefer, Patrick Faley, Emre O Neftci, Siddharth Joshi
Abstract	The energy efficiency of neuromorphic hardware is greatly affected by the energy of storing, accessing, and updating synaptic parameters. Various methods of memory organisation targeting energy-efficient digital accelerators have been investigated in the past, however, they do not completely encapsulate the energy costs at a system level. To address this shortcoming and to account for various overheads, we synthesize the controller and memory for different encoding schemes and extract the energy costs from these synthesized blocks. Additionally, we introduce functional encoding for structured connectivity such as the connectivity in convolutional layers. Functional encoding offers a 58% reduction in the energy to implement a backward pass and weight update in such layers compared to existing index-based solutions. We show that for a 2 layer spiking neural network trained to retain a spatio-temporal pattern, bitmap (PB-BMP) based organization can encode the sparser networks more efficiently. This form of encoding delivers a 1.37x improvement in energy efficiency coming at the cost of a 4% degradation in network retention accuracy as measured by the van Rossum distance.
Tasks
Published	2020-03-05
URL	https://arxiv.org/abs/2003.11639v1
PDF	https://arxiv.org/pdf/2003.11639v1.pdf
PWC	https://paperswithcode.com/paper/memory-organization-for-energy-efficient
Repo
Framework

An improved 3D region detection network: automated detection of the 12th thoracic vertebra in image guided radiation therapy


Title	An improved 3D region detection network: automated detection of the 12th thoracic vertebra in image guided radiation therapy
Authors	Yunhe Xie, Gregory Sharp, David P. Gierga, Theodore S. Hong, Thomas Bortfeld, Kongbin Kang
Abstract	Abstract. Image guidance has been widely used in radiation therapy. Correctly identifying anatomical landmarks, like the 12th thoracic vertebra (T12), is the key to success. Until recently, the detection of those landmarks still requires tedious manual inspections and annotations; and superior-inferior misalignment to the wrong vertebral body is still relatively common in image guided radiation therapy. It is necessary to develop an automated approach to detect those landmarks from images. There are three major challenges to identify T12 vertebra automatically: 1) subtle difference in the structures with high similarity, 2) limited annotated training data, and 3) high memory usage of 3D networks. Abstract. In this study, we propose a novel 3D full convolutional network (FCN) that is trained to detect anatomical structures from 3D volumetric data, requiring only a small amount of training data. Comparing with existing approaches, the network architecture, target generation and loss functions were significantly improved to address the challenges specific to medical images. In our experiments, the proposed network, which was trained from a small amount of annotated images, demonstrated the capability of accurately detecting structures with high similarity. Furthermore, the trained network showed the capability of cross-modality learning. This is meaningful in the situation where image annotations in one modality are easier to obtain than others. The cross-modality learning ability also indicated that the learned features were robust to noise in different image modalities. In summary, our approach has a great potential to be integrated into the clinical workflow to improve the safety of image guided radiation therapy.
Tasks
Published	2020-03-26
URL	https://arxiv.org/abs/2003.12163v1
PDF	https://arxiv.org/pdf/2003.12163v1.pdf
PWC	https://paperswithcode.com/paper/an-improved-3d-region-detection-network
Repo
Framework

Leveraging Schema Labels to Enhance Dataset Search


Title	Leveraging Schema Labels to Enhance Dataset Search
Authors	Zhiyu Chen, Haiyan Jia, Jeff Heflin, Brian D. Davison
Abstract	A search engine’s ability to retrieve desirable datasets is important for data sharing and reuse. Existing dataset search engines typically rely on matching queries to dataset descriptions. However, a user may not have enough prior knowledge to write a query using terms that match with description text.We propose a novel schema label generation model which generates possible schema labels based on dataset table content. We incorporate the generated schema labels into a mixed ranking model which not only considers the relevance between the query and dataset metadata but also the similarity between the query and generated schema labels. To evaluate our method on real-world datasets, we create a new benchmark specifically for the dataset retrieval task. Experiments show that our approach can effectively improve the precision and NDCG scores of the dataset retrieval task compared with baseline methods. We also test on a collection of Wikipedia tables to show that the features generated from schema labels can improve the unsupervised and supervised web table retrieval task as well.
Tasks
Published	2020-01-27
URL	https://arxiv.org/abs/2001.10112v1
PDF	https://arxiv.org/pdf/2001.10112v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-schema-labels-to-enhance-dataset
Repo
Framework

Face Verification via learning the kernel matrix


Title	Face Verification via learning the kernel matrix
Authors	Ning Yuan, Xiao-Jun Wu, He-Feng Yin
Abstract	The kernel function is introduced to solve the nonlinear pattern recognition problem. The advantage of a kernel method often depends critically on a proper choice of the kernel function. A promising approach is to learn the kernel from data automatically. Over the past few years, some methods which have been proposed to learn the kernel have some limitations: learning the parameters of some prespecified kernel function and so on. In this paper, the nonlinear face verification via learning the kernel matrix is proposed. A new criterion is used in the new algorithm to avoid inverting the possibly singular within-class which is a computational problem. The experimental results obtained on the facial database XM2VTS using the Lausanne protocol show that the verification performance of the new method is superior to that of the primary method Client Specific Kernel Discriminant Analysis (CSKDA). The method CSKDA needs to choose a proper kernel function through many experiments, while the new method could learn the kernel from data automatically which could save a lot of time and have the robust performance.
Tasks	Face Verification
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07323v1
PDF	https://arxiv.org/pdf/2001.07323v1.pdf
PWC	https://paperswithcode.com/paper/face-verification-via-learning-the-kernel
Repo
Framework

GRIDS: Interactive Layout Design with Integer Programming


Title	GRIDS: Interactive Layout Design with Integer Programming
Authors	Niraj Dayama, Kashyap Todi, Taru Saarelainen, Antti Oulasvirta
Abstract	Grid layouts are used by designers to spatially organise user interfaces when sketching and wireframing. However, their design is largely time consuming manual work. This is challenging due to combinatorial explosion and complex objectives, such as alignment, balance, and expectations regarding positions. This paper proposes a novel optimisation approach for the generation of diverse grid-based layouts. Our mixed integer linear programming (MILP) model offers a rigorous yet efficient method for grid generation that ensures packing, alignment, grouping, and preferential positioning of elements. Further, we present techniques for interactive diversification, enhancement, and completion of grid layouts (Figure 1). These capabilities are demonstrated using GRIDS1, a wireframing tool that provides designers with real-time layout suggestions. We report findings from a ratings study (N = 13) and a design study (N = 16), lending evidence for the benefit of computational grid generation during early stages of design.
Tasks
Published	2020-01-09
URL	https://arxiv.org/abs/2001.02921v1
PDF	https://arxiv.org/pdf/2001.02921v1.pdf
PWC	https://paperswithcode.com/paper/grids-interactive-layout-design-with-integer
Repo
Framework

Boosting Frank-Wolfe by Chasing Gradients


Title	Boosting Frank-Wolfe by Chasing Gradients
Authors	Cyrille W. Combettes, Sebastian Pokutta
Abstract	The Frank-Wolfe algorithm has become a popular first-order optimization algorithm for it is simple and projection-free, and it has been successfully applied to a variety of real-world problems. Its main drawback however lies in its convergence rate, which can be excessively slow due to naive descent directions. We propose to speed-up the Frank-Wolfe algorithm by better aligning the descent direction with that of the negative gradient via a subroutine. This subroutine chases the negative gradient direction in a matching pursuit-style while still preserving the projection-free property. Although the approach is reasonably natural, it produces very significant results. We derive convergence rates $\mathcal{O}(1/t)$ to $\mathcal{O}(e^{-\omega t^p})$ of our method where $p\in\left]0,1\right]$, and we demonstrate its competitive advantage both per iteration and in CPU time over the state-of-the-art in a series of computational experiments.
Tasks
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06369v1
PDF	https://arxiv.org/pdf/2003.06369v1.pdf
PWC	https://paperswithcode.com/paper/boosting-frank-wolfe-by-chasing-gradients
Repo
Framework

NeuroBoun: An inquiry-based approach for exploring scientific literature – a use case in neuroscience


Title	NeuroBoun: An inquiry-based approach for exploring scientific literature – a use case in neuroscience
Authors	S. Uskudarli, E. Gökdeniz, R. Canbeyli
Abstract	Online scientific publications provide vast opportunities for researchers. Alas, the quantity and the rate of increase in the articles make the utilization of these resources very challenging. This work presents as inquiry-based approach to support the articulation of complex inter-related queries to gain insights regarding how these subjects have been studied in conjunction with one another as reported in the scientific literature. For this purpose we introduce inquiries that represent inter-related subqueries that are of interest to a researcher. The inquiries are expanded to better capture the intent of the inquirer, from which several queries are generated that represent various juxtapositions of the subjects in consideration. The sets of queries are used to search repositories to yield results that reveal quantitative and temporal relations among the subjects of the inquiry. A web-based tool, NeuroBoun, is developed as a proof of concept for medical publications found in PubMed. A use case related to the asymmetry of amygdala is presented to illustrate the potentials of the proposed approach.
Tasks
Published	2020-01-01
URL	https://arxiv.org/abs/2001.00186v1
PDF	https://arxiv.org/pdf/2001.00186v1.pdf
PWC	https://paperswithcode.com/paper/neuroboun-an-inquiry-based-approach-for
Repo
Framework

Cutoff for exact recovery of Gaussian mixture models


Title	Cutoff for exact recovery of Gaussian mixture models
Authors	Xiaohui Chen, Yun Yang
Abstract	We determine the cutoff value on separation of cluster centers for exact recovery of cluster labels in a $K$-component Gaussian mixture model with equal cluster sizes. Moreover, we show that a semidefinite programming (SDP) relaxation of the $K$-means clustering method achieves such sharp threshold for exact recovery without assuming the symmetry of cluster centers.
Tasks
Published	2020-01-05
URL	https://arxiv.org/abs/2001.01194v1
PDF	https://arxiv.org/pdf/2001.01194v1.pdf
PWC	https://paperswithcode.com/paper/cutoff-for-exact-recovery-of-gaussian-mixture
Repo
Framework

Deep Nearest Neighbor Anomaly Detection


Title	Deep Nearest Neighbor Anomaly Detection
Authors	Liron Bergman, Niv Cohen, Yedid Hoshen
Abstract	Nearest neighbors is a successful and long-standing technique for anomaly detection. Significant progress has been recently achieved by self-supervised deep methods (e.g. RotNet). Self-supervised features however typically under-perform Imagenet pre-trained features. In this work, we investigate whether the recent progress can indeed outperform nearest-neighbor methods operating on an Imagenet pretrained feature space. The simple nearest-neighbor based-approach is experimentally shown to outperform self-supervised methods in: accuracy, few shot generalization, training time and noise robustness while making fewer assumptions on image distributions.
Tasks	Anomaly Detection
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10445v1
PDF	https://arxiv.org/pdf/2002.10445v1.pdf
PWC	https://paperswithcode.com/paper/deep-nearest-neighbor-anomaly-detection
Repo
Framework