January 29, 2020

2878 words 14 mins read

Paper Group ANR 638

Butterfly-Net2: Simplified Butterfly-Net and Fourier Transform Initialization. Embedding Imputation with Grounded Language Information. Online Variance Reduction with Mixtures. Point cloud registration: matching a maximal common subset on pointclouds with noise (with 2D implementation). What Do We Really Need? Degenerating U-Net on Retinal Vessel S …

Butterfly-Net2: Simplified Butterfly-Net and Fourier Transform Initialization


Title	Butterfly-Net2: Simplified Butterfly-Net and Fourier Transform Initialization
Authors	Zhongshu Xu, Yingzhou Li, Xiuyuan Cheng
Abstract	Structured CNN designed using the prior information of problems potentially improves efficiency over conventional CNNs in various tasks in solving PDEs and inverse problems in signal processing. This paper introduces BNet2, a simplified Butterfly-Net and inline with the conventional CNN. Moreover, a Fourier transform initialization is proposed for both BNet2 and CNN with guaranteed approximation power to represent the Fourier transform operator. Experimentally, BNet2 and the Fourier transform initialization strategy are tested on various tasks, including approximating Fourier transform operator, end-to-end solvers of linear and nonlinear PDEs in 1D, and denoising and deblurring of 1D signals. On all tasks, under the same initialization, BNet2 achieves similar accuracy as CNN but has fewer parameters. Fourier transform initialized BNet2 and CNN consistently improve the training and testing accuracy over the randomly initialized CNN.
Tasks	Deblurring, Denoising
Published	2019-12-09
URL	https://arxiv.org/abs/1912.04154v1
PDF	https://arxiv.org/pdf/1912.04154v1.pdf
PWC	https://paperswithcode.com/paper/butterfly-net2-simplified-butterfly-net-and
Repo
Framework

Embedding Imputation with Grounded Language Information


Title	Embedding Imputation with Grounded Language Information
Authors	Ziyi Yang, Chenguang Zhu, Vin Sachidananda, Eric Darve
Abstract	Due to the ubiquitous use of embeddings as input representations for a wide range of natural language tasks, imputation of embeddings for rare and unseen words is a critical problem in language processing. Embedding imputation involves learning representations for rare or unseen words during the training of an embedding model, often in a post-hoc manner. In this paper, we propose an approach for embedding imputation which uses grounded information in the form of a knowledge graph. This is in contrast to existing approaches which typically make use of vector space properties or subword information. We propose an online method to construct a graph from grounded information and design an algorithm to map from the resulting graphical structure to the space of the pre-trained embeddings. Finally, we evaluate our approach on a range of rare and unseen word tasks across various domains and show that our model can learn better representations. For example, on the Card-660 task our method improves Pearson’s and Spearman’s correlation coefficients upon the state-of-the-art by 11% and 17.8% respectively using GloVe embeddings.
Tasks	Imputation
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03753v1
PDF	https://arxiv.org/pdf/1906.03753v1.pdf
PWC	https://paperswithcode.com/paper/embedding-imputation-with-grounded-language
Repo
Framework

Online Variance Reduction with Mixtures


Title	Online Variance Reduction with Mixtures
Authors	Zalán Borsos, Sebastian Curi, Kfir Y. Levy, Andreas Krause
Abstract	Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction. In this work, we propose a new framework for variance reduction that enables the use of mixtures over predefined sampling distributions, which can naturally encode prior knowledge about the data. While these sampling distributions are fixed, the mixture weights are adapted during the optimization process. We propose VRM, a novel and efficient adaptive scheme that asymptotically recovers the best mixture weights in hindsight and can also accommodate sampling distributions over sets of points. We empirically demonstrate the versatility of VRM in a range of applications.
Tasks	Stochastic Optimization
Published	2019-03-29
URL	http://arxiv.org/abs/1903.12416v1
PDF	http://arxiv.org/pdf/1903.12416v1.pdf
PWC	https://paperswithcode.com/paper/online-variance-reduction-with-mixtures
Repo
Framework

Point cloud registration: matching a maximal common subset on pointclouds with noise (with 2D implementation)


Title	Point cloud registration: matching a maximal common subset on pointclouds with noise (with 2D implementation)
Authors	Jorge Arce Garro, David Jiménez López
Abstract	We analyze the problem of determining whether 2 given point clouds in 2D, with any distinct cardinality and any number of outliers, have subsets of the same size that can be matched via a rigid motion. This problem is important, for example, in the application of fingerprint matching with incomplete data. We propose an algorithm that, under assumptions on the noise tolerance, allows to find corresponding subclouds of the maximum possible size. Our procedure optimizes a potential energy function to do so, which was first inspired in the potential energy interaction that occurs between point charges in electrostatics.
Tasks	Point Cloud Registration
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07454v1
PDF	http://arxiv.org/pdf/1904.07454v1.pdf
PWC	https://paperswithcode.com/paper/point-cloud-registration-matching-a-maximal
Repo
Framework

What Do We Really Need? Degenerating U-Net on Retinal Vessel Segmentation


Title	What Do We Really Need? Degenerating U-Net on Retinal Vessel Segmentation
Authors	Weilin Fu, Katharina Breininger, Zhaoya Pan, Andreas Maier
Abstract	Retinal vessel segmentation is an essential step for fundus image analysis. With the recent advances of deep learning technologies, many convolutional neural networks have been applied in this field, including the successful U-Net. In this work, we firstly modify the U-Net with functional blocks aiming to pursue higher performance. The absence of the expected performance boost then lead us to dig into the opposite direction of shrinking the U-Net and exploring the extreme conditions such that its segmentation performance is maintained. Experiment series to simplify the network structure, reduce the network size and restrict the training conditions are designed. Results show that for retinal vessel segmentation on DRIVE database, U-Net does not degenerate until surprisingly acute conditions: one level, one filter in convolutional layers, and one training sample. This experimental discovery is both counter-intuitive and worthwhile. Not only are the extremes of the U-Net explored on a well-studied application, but also one intriguing warning is raised for the research methodology which seeks for marginal performance enhancement regardless of the resource cost.
Tasks	Retinal Vessel Segmentation
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02660v1
PDF	https://arxiv.org/pdf/1911.02660v1.pdf
PWC	https://paperswithcode.com/paper/what-do-we-really-need-degenerating-u-net-on
Repo
Framework

ICPS-net: An End-to-End RGB-based Indoor Camera Positioning System using deep convolutional neural networks


Title	ICPS-net: An End-to-End RGB-based Indoor Camera Positioning System using deep convolutional neural networks
Authors	Ali Ghofrani, Rahil Mahdian Toroghi, Sayed Mojtaba Tabatabaie
Abstract	Indoor positioning and navigation inside an area with no GPS-data availability is a challenging problem. There are applications such as augmented reality, autonomous driving, navigation of drones inside tunnels, in which indoor positioning gets crucial. In this paper, a tandem architecture of deep network-based systems, for the first time to our knowledge, is developed to address this problem. This structure is trained on the scene images being obtained through scanning of the desired area segments using photogrammetry. A CNN structure based on EfficientNet is trained as a classifier of the scenes, followed by a MobileNet CNN structure which is trained to perform as a regressor. The proposed system achieves amazingly fine precisions for both Cartesian position and Quaternion information of the camera.
Tasks	Autonomous Driving
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06219v1
PDF	https://arxiv.org/pdf/1910.06219v1.pdf
PWC	https://paperswithcode.com/paper/icps-net-an-end-to-end-rgb-based-indoor
Repo
Framework

Weakly Supervised Multi-Task Learning for Cell Detection and Segmentation


Title	Weakly Supervised Multi-Task Learning for Cell Detection and Segmentation
Authors	Alireza Chamanzar, Yao Nie
Abstract	Cell detection and segmentation is fundamental for all downstream analysis of digital pathology images. However, obtaining the pixel-level ground truth for single cell segmentation is extremely labor intensive. To overcome this challenge, we developed an end-to-end deep learning algorithm to perform both single cell detection and segmentation using only point labels. This is achieved through the combination of different task orientated point label encoding methods and a multi-task scheduler for training. We apply and validate our algorithm on PMS2 stained colon rectal cancer and tonsil tissue images. Compared to the state-of-the-art, our algorithm shows significant improvement in cell detection and segmentation without increasing the annotation efforts.
Tasks	Cell Segmentation, Multi-Task Learning
Published	2019-10-27
URL	https://arxiv.org/abs/1910.12326v1
PDF	https://arxiv.org/pdf/1910.12326v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-multi-task-learning-for
Repo
Framework

Comparing Deep Learning Models for Multi-cell Classification in Liquid-based Cervical Cytology Images


Title	Comparing Deep Learning Models for Multi-cell Classification in Liquid-based Cervical Cytology Images
Authors	Sudhir Sornapudi, G. T. Brown, Zhiyun Xue, Rodney Long, Lisa Allen, Sameer Antani
Abstract	Liquid-based cytology (LBC) is a reliable automated technique for the screening of Papanicolaou (Pap) smear data. It is an effective technique for collecting a majority of the cervical cells and aiding cytopathologists in locating abnormal cells. Most methods published in the research literature rely on accurate cell segmentation as a prior, which remains challenging due to a variety of factors, e.g., stain consistency, presence of clustered cells, etc. We propose a method for automatic classification of cervical slide images through generation of labeled cervical patch data and extracting deep hierarchical features by fine-tuning convolution neural networks, as well as a novel graph-based cell detection approach for cellular level evaluation. The results show that the proposed pipeline can classify images of both single cell and overlapping cells. The VGG-19 model is found to be the best at classifying the cervical cytology patch data with 95 % accuracy under precision-recall curve.
Tasks	Cell Segmentation
Published	2019-10-02
URL	https://arxiv.org/abs/1910.00722v1
PDF	https://arxiv.org/pdf/1910.00722v1.pdf
PWC	https://paperswithcode.com/paper/comparing-deep-learning-models-for-multi-cell
Repo
Framework

Geovisual Analytics and Interactive Machine Learning for Situational Awareness


Title	Geovisual Analytics and Interactive Machine Learning for Situational Awareness
Authors	Morteza Karimzadeh, Luke S. Snyder, David S. Ebert
Abstract	The first responder community has traditionally relied on calls from the public, officially-provided geographic information and maps for coordinating actions on the ground. The ubiquity of social media platforms created an opportunity for near real-time sensing of the situation (e.g. unfolding weather events or crises) through volunteered geographic information. In this article, we provide an overview of the design process and features of the Social Media Analytics Reporting Toolkit (SMART), a visual analytics platform developed at Purdue University for providing first responders with real-time situational awareness. We attribute its successful adoption by many first responders to its user-centered design, interactive (geo)visualizations and interactive machine learning, giving users control over analysis.
Tasks
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05441v1
PDF	https://arxiv.org/pdf/1910.05441v1.pdf
PWC	https://paperswithcode.com/paper/geovisual-analytics-and-interactive-machine
Repo
Framework

Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor


Title	Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor
Authors	Daniel Seita, Aditya Ganapathi, Ryan Hoque, Minho Hwang, Edward Cen, Ajay Kumar Tanwani, Ashwin Balakrishna, Brijen Thananjeyan, Jeffrey Ichnowski, Nawid Jamali, Katsu Yamane, Soshi Iba, John Canny, Ken Goldberg
Abstract	Sequential pulling policies to flatten and smooth fabrics have applications from surgery to manufacturing to home tasks such as bed making and folding clothes. Due to the complexity of fabric states and dynamics, we apply deep imitation learning to learn policies that, given color (RGB), depth (D), or combined color-depth (RGBD) images of a rectangular fabric sample, estimate pick points and pull vectors to spread the fabric to maximize coverage. To generate data, we develop a fabric simulator and an algorithmic supervisor that has access to complete state information. We train policies in simulation using domain randomization and dataset aggregation (DAgger) on three tiers of difficulty in the initial randomized configuration. We present results comparing five baseline policies to learned policies and report systematic comparisons of RGB vs D vs RGBD images as inputs. In simulation, learned policies achieve comparable or superior performance to analytic baselines. In 180 physical experiments with the da Vinci Research Kit (dVRK) surgical robot, RGBD policies trained in simulation attain coverage of 83% to 95% depending on difficulty tier, suggesting that effective fabric smoothing policies can be learned from an algorithmic supervisor and that depth sensing is a valuable addition to color alone. Supplementary material is available at https://sites.google.com/view/fabric-smoothing.
Tasks	Imitation Learning
Published	2019-09-23
URL	https://arxiv.org/abs/1910.04854v2
PDF	https://arxiv.org/pdf/1910.04854v2.pdf
PWC	https://paperswithcode.com/paper/deep-imitation-learning-of-sequential-fabric
Repo
Framework

QANet – Quality Assurance Network for Image Segmentation


Title	QANet – Quality Assurance Network for Image Segmentation
Authors	Assaf Arbelle, Eliav Elul, Tammy Riklin Raviv
Abstract	We introduce a novel Deep Learning framework, which quantitatively estimates image segmentation quality without the need for human inspection or labeling. We refer to this method as a Quality Assurance Network – QANet. Specifically, given an image and a `proposed’ corresponding segmentation, obtained by any method including manual annotation, the QANet solves a regression problem in order to estimate a predefined quality measure with respect to the unknown ground truth. The QANet is by no means yet another segmentation method. Instead, it performs a multi-level, multi-feature comparison of an image-segmentation pair based on a unique network architecture, called the RibCage. To demonstrate the strength of the QANet, we addressed the evaluation of instance segmentation using two different datasets from different domains, namely, high throughput live cell microscopy images from the Cell Segmentation Benchmark and natural images of plants from the Leaf Segmentation Challenge. While synthesized segmentations were used to train the QANet, it was tested on segmentations obtained by publicly available methods that participated in the different challenges. We show that the QANet accurately estimates the scores of the evaluated segmentations with respect to the hidden ground truth, as published by the challenges’ organizers. The code is available at: TBD. \|
Tasks	Cell Segmentation, Instance Segmentation, Semantic Segmentation
Published	2019-04-09
URL	https://arxiv.org/abs/1904.08503v5
PDF	https://arxiv.org/pdf/1904.08503v5.pdf
PWC	https://paperswithcode.com/paper/190408503
Repo
Framework

Teaching AI, Ethics, Law and Policy


Title	Teaching AI, Ethics, Law and Policy
Authors	Asher Wilk
Abstract	The cyberspace and development of intelligent systems using Artificial Intelligence (AI) creates new challenges to computer professionals, data scientists, regulators and policy makers. For example, self-driving cars raise new technical, ethical, legal and public policy issues. This paper proposes a course named Computers, Ethics, Law, and Public Policy, and suggests a curriculum for such a course. This paper presents ethical, legal, and public policy issues relevant to building and using intelligent systems.
Tasks	Self-Driving Cars
Published	2019-04-29
URL	https://arxiv.org/abs/1904.12470v5
PDF	https://arxiv.org/pdf/1904.12470v5.pdf
PWC	https://paperswithcode.com/paper/teaching-ai-ethics-law-and-policy
Repo
Framework

Structural Health Monitoring of Cantilever Beam, a Case Study – Using Bayesian Neural Network AND Deep Learning


Title	Structural Health Monitoring of Cantilever Beam, a Case Study – Using Bayesian Neural Network AND Deep Learning
Authors	Rahul Vashisht, H. Viji, T. Sundararajan, D. Mohankumar, S. Sumitra
Abstract	The advancement of machine learning algorithms has opened a wide scope for vibration-based SHM (Structural Health Monitoring). Vibration-based SHM is based on the fact that damage will alter the dynamic properties viz., structural response, frequencies, mode shapes, etc of the structure. The responses measured using sensors, which are high dimensional in nature, can be intelligently analyzed using machine learning techniques for damage assessment. Neural networks employing multilayer architectures are expressive models capable of capturing complex relationships between input-output pairs but do not account for uncertainty in network outputs. A BNN (Bayesian Neural Network) refers to extending standard networks with posterior inference. It is a neural network with a prior distribution on its weights. Deep learning architectures like CNN (Convolutional neural network) and LSTM(Long Short Term Memory) are good candidates for representation learning from high dimensional data. The advantage of using CNN over multi-layer neural networks is that they are good feature extractors as well as classifiers, which eliminates the need for generating hand-engineered features. LSTM networks are mainly used for sequence modeling. This paper presents both a Bayesian multi-layer perceptron and deep learning-based approach for damage detection and location identification in beam-like structures. Raw frequency response data simulated using finite element analysis is fed as the input of the network. As part of this, frequency response was generated for a series of simulations in the cantilever beam involving different damage scenarios. This case study shows the effectiveness of the above approaches to predict bending rigidity with an acceptable error rate.
Tasks	Cantilever Beam, Representation Learning
Published	2019-08-17
URL	https://arxiv.org/abs/1908.06326v1
PDF	https://arxiv.org/pdf/1908.06326v1.pdf
PWC	https://paperswithcode.com/paper/structural-health-monitoring-of-cantilever
Repo
Framework

Highly Efficient Follicular Segmentation in Thyroid Cytopathological Whole Slide Image


Title	Highly Efficient Follicular Segmentation in Thyroid Cytopathological Whole Slide Image
Authors	Siyan Tao, Yao Guo, Chuang Zhu, Huang Chen, Yue Zhang, Jie Yang, Jun Liu
Abstract	In this paper, we propose a novel method for highly efficient follicular segmentation of thyroid cytopathological WSIs. Firstly, we propose a hybrid segmentation architecture, which integrates a classifier into Deeplab V3 by adding a branch. A large amount of the WSI segmentation time is saved by skipping the irrelevant areas using the classification branch. Secondly, we merge the low scale fine features into the original atrous spatial pyramid pooling (ASPP) in Deeplab V3 to accurately represent the details in cytopathological images. Thirdly, our hybrid model is trained by a criterion-oriented adaptive loss function, which leads the model converging much faster. Experimental results on a collection of thyroid patches demonstrate that the proposed model reaches 80.9% on the segmentation accuracy. Besides, 93% time is reduced for the WSI segmentation by using our proposed method, and the WSI-level accuracy achieves 53.4%.
Tasks
Published	2019-02-13
URL	http://arxiv.org/abs/1902.05431v1
PDF	http://arxiv.org/pdf/1902.05431v1.pdf
PWC	https://paperswithcode.com/paper/highly-efficient-follicular-segmentation-in
Repo
Framework

Autonomous Cars: Vision based Steering Wheel Angle Estimation


Title	Autonomous Cars: Vision based Steering Wheel Angle Estimation
Authors	Kemal Alkin Gunbay, Mert Arikan, Mehmet Turkan
Abstract	Machine learning models, which are frequently used in self-driving cars, are trained by matching the captured images of the road and the measured angle of the steering wheel. The angle of the steering wheel is generally fetched from steering angle sensor, which is tightly-coupled to the physical aspects of the vehicle at hand. Therefore, a model-agnostic autonomous car-kit is very difficult to be developed and autonomous vehicles need more training data. The proposed vision based steering angle estimation system argues a new approach which basically matches the images of the road captured by an outdoor camera and the images of the steering wheel from an onboard camera, avoiding the burden of collecting model-dependent training data and the use of any other electromechanical hardware.
Tasks	Autonomous Vehicles, Self-Driving Cars
Published	2019-01-30
URL	http://arxiv.org/abs/1901.10747v1
PDF	http://arxiv.org/pdf/1901.10747v1.pdf
PWC	https://paperswithcode.com/paper/autonomous-cars-vision-based-steering-wheel
Repo
Framework