April 3, 2020

3263 words 16 mins read

Paper Group ANR 13

Paper Group ANR 13

Coronavirus (COVID-19) Classification using CT Images by Machine Learning Methods. Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection. Sketch-to-Art: Synthesizing Stylized Art Images From Sketches. iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection. From Fourier to Koopman: Spec …

Coronavirus (COVID-19) Classification using CT Images by Machine Learning Methods

Title Coronavirus (COVID-19) Classification using CT Images by Machine Learning Methods
Authors Mucahid Barstugan, Umut Ozkaya, Saban Ozturk
Abstract This study presents early phase detection of Coronavirus (COVID-19), which is named by World Health Organization (WHO), by machine learning methods. The detection process was implemented on abdominal Computed Tomography (CT) images. The expert radiologists detected from CT images that COVID-19 shows different behaviours from other viral pneumonia. Therefore, the clinical experts specify that COV.ID-19 virus needs to be diagnosed in early phase. For detection of the COVID-19, four different datasets were formed by taking patches sized as 16x16, 32x32, 48x48, 64x64 from 150 CT images. The feature extraction process was applied to patches to increase the classification performance. Grey Level Co-occurrence Matrix (GLCM), Local Directional Pattern (LDP), Grey Level Run Length Matrix (GLRLM), Grey-Level Size Zone Matrix (GLSZM), and Discrete Wavelet Transform (DWT) algorithms were used as feature extraction methods. Support Vector Machines (SVM) classified the extracted features. 2-fold, 5-fold and 10-fold cross-validations were implemented during the classification process. Sensitivity, specificity, accuracy, precision, and F-score metrics were used to evaluate the classification performance. The best classification accuracy was obtained as 99.68% with 10-fold cross-validation and GLSZM feature extraction method.
Tasks Computed Tomography (CT)
Published 2020-03-20
URL https://arxiv.org/abs/2003.09424v1
PDF https://arxiv.org/pdf/2003.09424v1.pdf
PWC https://paperswithcode.com/paper/coronavirus-covid-19-classification-using-ct

Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection

Title Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection
Authors Biraja Ghoshal, Allan Tucker
Abstract Deep Learning has achieved state of the art performance in medical imaging. However, these methods for disease detection focus exclusively on improving the accuracy of classification or predictions without quantifying uncertainty in a decision. Knowing how much confidence there is in a computer-based medical diagnosis is essential for gaining clinicians trust in the technology and therefore improve treatment. Today, the 2019 Coronavirus (SARS-CoV-2) infections are a major healthcare challenge around the world. Detecting COVID-19 in X-ray images is crucial for diagnosis, assessment and treatment. However, diagnostic uncertainty in the report is a challenging and yet inevitable task for radiologist. In this paper, we investigate how drop-weights based Bayesian Convolutional Neural Networks (BCNN) can estimate uncertainty in Deep Learning solution to improve the diagnostic performance of the human-machine team using publicly available COVID-19 chest X-ray dataset and show that the uncertainty in prediction is highly correlates with accuracy of prediction. We believe that the availability of uncertainty-aware deep learning solution will enable a wider adoption of Artificial Intelligence (AI) in a clinical setting.
Tasks COVID-19 Detection, Medical Diagnosis
Published 2020-03-22
URL https://arxiv.org/abs/2003.10769v2
PDF https://arxiv.org/pdf/2003.10769v2.pdf
PWC https://paperswithcode.com/paper/estimating-uncertainty-and-interpretability

Sketch-to-Art: Synthesizing Stylized Art Images From Sketches

Title Sketch-to-Art: Synthesizing Stylized Art Images From Sketches
Authors Bingchen Liu, Kunpeng Song, Ahmed Elgammal
Abstract We propose a new approach for synthesizing fully detailed art-stylized images from sketches. Given a sketch, with no semantic tagging, and a reference image of a specific style, the model can synthesize meaningful details with colors and textures. The model consists of three modules designed explicitly for better artistic style capturing and generation. Based on a GAN framework, a dual-masked mechanism is introduced to enforce the content constraints (from the sketch), and a feature-map transformation technique is developed to strengthen the style consistency (to the reference image). Finally, an inverse procedure of instance-normalization is proposed to disentangle the style and content information, therefore yields better synthesis performance. Experiments demonstrate a significant qualitative and quantitative boost over baselines based on previous state-of-the-art techniques, adopted for the proposed process.
Published 2020-02-26
URL https://arxiv.org/abs/2002.12888v2
PDF https://arxiv.org/pdf/2002.12888v2.pdf
PWC https://paperswithcode.com/paper/sketch-to-art-synthesizing-stylized-art

iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection

Title iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
Authors Chenfan Zhuang, Xintong Han, Weilin Huang, Matthew R. Scott
Abstract Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive object detection has verified that aligning data distributions between source and target images through adversarial learning is very useful. The key is when, where and how to use it to achieve best practice. We propose Image-Instance Full Alignment Networks (iFAN) to tackle this problem by precisely aligning feature distributions on both image and instance levels: 1) Image-level alignment: multi-scale features are roughly aligned by training adversarial domain classifiers in a hierarchically-nested fashion. 2) Full instance-level alignment: deep semantic information and elaborate instance representations are fully exploited to establish a strong relationship among categories and domains. Establishing these correlations is formulated as a metric learning problem by carefully constructing instance pairs. Above-mentioned adaptations can be integrated into an object detector (e.g. Faster RCNN), resulting in an end-to-end trainable framework where multiple alignments can work collaboratively in a coarse-tofine manner. In two domain adaptation tasks: synthetic-to-real (SIM10K->Cityscapes) and normal-to-foggy weather (Cityscapes->Foggy Cityscapes), iFAN outperforms the state-of-the-art methods with a boost of 10%+ AP over the source-only baseline.
Tasks Domain Adaptation, Metric Learning, Object Detection
Published 2020-03-09
URL https://arxiv.org/abs/2003.04132v1
PDF https://arxiv.org/pdf/2003.04132v1.pdf
PWC https://paperswithcode.com/paper/ifan-image-instance-full-alignment-networks

From Fourier to Koopman: Spectral Methods for Long-term Time Series Prediction

Title From Fourier to Koopman: Spectral Methods for Long-term Time Series Prediction
Authors Henning Lange, Steven L. Brunton, Nathan Kutz
Abstract We propose spectral methods for long-term forecasting of temporal signals stemming from linear and nonlinear quasi-periodic dynamical systems. For linear signals, we introduce an algorithm with similarities to the Fourier transform but which does not rely on periodicity assumptions, allowing for forecasting given potentially arbitrary sampling intervals. We then extend this algorithm to handle nonlinearities by leveraging Koopman theory. The resulting algorithm performs a spectral decomposition in a nonlinear, data-dependent basis. The optimization objective for both algorithms is highly non-convex. However, expressing the objective in the frequency domain allows us to compute global optima of the error surface in a scalable and efficient manner, partially by exploiting the computational properties of the Fast Fourier Transform. Because of their close relation to Bayesian Spectral Analysis, uncertainty quantification metrics are a natural byproduct of the spectral forecasting methods. We extensively benchmark these algorithms against other leading forecasting methods on a range of synthetic experiments as well as in the context of real-world power systems and fluid flows.
Tasks Time Series, Time Series Prediction
Published 2020-04-01
URL https://arxiv.org/abs/2004.00574v1
PDF https://arxiv.org/pdf/2004.00574v1.pdf
PWC https://paperswithcode.com/paper/from-fourier-to-koopman-spectral-methods-for

S-APIR: News-based Business Sentiment Index

Title S-APIR: News-based Business Sentiment Index
Authors Kazuhiro Seki, Yusuke Ikuta
Abstract This paper describes our work on developing a new business sentiment index using daily newspaper articles. We adopt a recurrent neural network (RNN) with Gated Recurrent Units to predict the business sentiment of a given text. An RNN is initially trained on Economy Watchers Survey and then fine-tuned on news texts for domain adaptation. Also, a one-class support vector machine is applied to filter out texts deemed irrelevant to business sentiment. Moreover, we propose a simple approach to temporally analyzing how much and when any given factor influences the predicted business sentiment. The validity and utility of the proposed approaches are empirically demonstrated through a series of experiments on Nikkei Newspaper articles published from 2013 to 2018.
Tasks Domain Adaptation
Published 2020-03-06
URL https://arxiv.org/abs/2003.02973v1
PDF https://arxiv.org/pdf/2003.02973v1.pdf
PWC https://paperswithcode.com/paper/s-apir-news-based-business-sentiment-index

Towards Fair Cross-Domain Adaptation via Generative Learning

Title Towards Fair Cross-Domain Adaptation via Generative Learning
Authors Tongxin Wang, Zhengming Ding, Wei Shao, Haixu Tang, Kun Huang
Abstract Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions. Existing DA normally assumes the well-labeled source domain is class-wise balanced, which means the size per source class is relatively similar. However, in real-world applications, labeled samples for some categories in the source domain could be extremely few due to the difficulty of data collection and annotation, which leads to decreasing performance over target domain on those few-shot categories. To perform fair cross-domain adaptation and boost the performance on these minority categories, we develop a novel Generative Few-shot Cross-domain Adaptation (GFCA) algorithm for fair cross-domain classification. Specifically, generative feature augmentation is explored to synthesize effective training data for few-shot source classes, while effective cross-domain alignment aims to adapt knowledge from source to facilitate the target learning. Experimental results on two large cross-domain visual datasets demonstrate the effectiveness of our proposed method on improving both few-shot and overall classification accuracy comparing with the state-of-the-art DA approaches.
Tasks Domain Adaptation
Published 2020-03-04
URL https://arxiv.org/abs/2003.02366v1
PDF https://arxiv.org/pdf/2003.02366v1.pdf
PWC https://paperswithcode.com/paper/towards-fair-cross-domain-adaptation-via

Non-Volatile Memory Array Based Quantization- and Noise-Resilient LSTM Neural Networks

Title Non-Volatile Memory Array Based Quantization- and Noise-Resilient LSTM Neural Networks
Authors Wen Ma, Pi-Feng Chiu, Won Ho Choi, Minghai Qin, Daniel Bedau, Martin Lueker-Boden
Abstract In cloud and edge computing models, it is important that compute devices at the edge be as power efficient as possible. Long short-term memory (LSTM) neural networks have been widely used for natural language processing, time series prediction and many other sequential data tasks. Thus, for these applications there is increasing need for low-power accelerators for LSTM model inference at the edge. In order to reduce power dissipation due to data transfers within inference devices, there has been significant interest in accelerating vector-matrix multiplication (VMM) operations using non-volatile memory (NVM) weight arrays. In NVM array-based hardware, reduced bit-widths also significantly increases the power efficiency. In this paper, we focus on the application of quantization-aware training algorithm to LSTM models, and the benefits these models bring in terms of resilience against both quantization error and analog device noise. We have shown that only 4-bit NVM weights and 4-bit ADC/DACs are needed to produce equivalent LSTM network performance as floating-point baseline. Reasonable levels of ADC quantization noise and weight noise can be naturally tolerated within our NVMbased quantized LSTM network. Benchmark analysis of our proposed LSTM accelerator for inference has shown at least 2.4x better computing efficiency and 40x higher area efficiency than traditional digital approaches (GPU, FPGA, and ASIC). Some other novel approaches based on NVM promise to deliver higher computing efficiency (up to 4.7x) but require larger arrays with potential higher error rates.
Tasks Quantization, Time Series, Time Series Prediction
Published 2020-02-25
URL https://arxiv.org/abs/2002.10636v1
PDF https://arxiv.org/pdf/2002.10636v1.pdf
PWC https://paperswithcode.com/paper/non-volatile-memory-array-based-quantization

Knowledge synthesis from 100 million biomedical documents augments the deep expression profiling of coronavirus receptors

Title Knowledge synthesis from 100 million biomedical documents augments the deep expression profiling of coronavirus receptors
Authors AJ Venkatakrishnan, Arjun Puranik, Akash Anand, David Zemmour, Xiang Yao, Xiaoying Wu, Ramakrishna Chilaka, Dariusz K. Murakowski, Kristopher Standish, Bharathwaj Raghunathan, Tyler Wagner, Enrique Garcia-Rivera, Hugo Solomon, Abhinav Garg, Rakesh Barve, Anuli Anyanwu-Ofili, Najat Khan, Venky Soundararajan
Abstract The COVID-19 pandemic demands assimilation of all available biomedical knowledge to decode its mechanisms of pathogenicity and transmission. Despite the recent renaissance in unsupervised neural networks for decoding unstructured natural languages, a platform for the real-time synthesis of the exponentially growing biomedical literature and its comprehensive triangulation with deep omic insights is not available. Here, we present the nferX platform for dynamic inference from over 45 quadrillion possible conceptual associations extracted from unstructured biomedical text, and their triangulation with Single Cell RNA-sequencing based insights from over 25 tissues. Using this platform, we identify intersections between the pathologic manifestations of COVID-19 and the comprehensive expression profile of the SARS-CoV-2 receptor ACE2. We find that tongue keratinocytes and olfactory epithelial cells are likely under-appreciated targets of SARS-CoV-2 infection, correlating with reported loss of sense of taste and smell as early indicators of COVID-19 infection, including in otherwise asymptomatic patients. Airway club cells, ciliated cells and type II pneumocytes in the lung, and enterocytes of the gut also express ACE2. This study demonstrates how a holistic data science platform can leverage unprecedented quantities of structured and unstructured publicly available data to accelerate the generation of impactful biological insights and hypotheses.
Published 2020-03-28
URL https://arxiv.org/abs/2003.12773v1
PDF https://arxiv.org/pdf/2003.12773v1.pdf
PWC https://paperswithcode.com/paper/knowledge-synthesis-from-100-million

Efficient and Effective Similar Subtrajectory Search with Deep Reinforcement Learning

Title Efficient and Effective Similar Subtrajectory Search with Deep Reinforcement Learning
Authors Zheng Wang, Cheng Long, Gao Cong, Yiding Liu
Abstract Similar trajectory search is a fundamental problem and has been well studied over the past two decades. However, the similar subtrajectory search (SimSub) problem, aiming to return a portion of a trajectory (i.e., a subtrajectory) which is the most similar to a query trajectory, has been mostly disregarded despite that it could capture trajectory similarity in a finer-grained way and many applications take subtrajectories as basic units for analysis. In this paper, we study the SimSub problem and develop a suite of algorithms including both exact and approximate ones. Among those approximate algorithms, two that are based on deep reinforcement learning stand out and outperform those non-learning based algorithms in terms of effectiveness and efficiency. We conduct experiments on real-world trajectory datasets, which verify the effectiveness and efficiency of the proposed algorithms.
Published 2020-03-05
URL https://arxiv.org/abs/2003.02542v1
PDF https://arxiv.org/pdf/2003.02542v1.pdf
PWC https://paperswithcode.com/paper/efficient-and-effective-similar-subtrajectory

Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning

Title Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning
Authors Byungsoo Ko, Geonmo Gu
Abstract Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on metric learning losses for augmentation and generalization. However, these methods require additional generative networks along with the main network, which can lead to a larger model size, slower training speed, and harder optimization. Meanwhile, post-processing techniques, such as query expansion and database augmentation, have proposed the combination of feature points to obtain additional semantic information. In this paper, inspired by query expansion and database augmentation, we propose an augmentation method in an embedding space for pair-based metric learning losses, called embedding expansion. The proposed method generates synthetic points containing augmented information by a combination of feature points and performs hard negative pair mining to learn with the most informative feature representations. Because of its simplicity and flexibility, it can be used for existing metric learning losses without affecting model size, training speed, or optimization difficulty. Finally, the combination of embedding expansion and representative metric learning losses outperforms the state-of-the-art losses and previous sample generation methods in both image retrieval and clustering tasks. The implementation will be publicly available.
Tasks Image Retrieval, Metric Learning
Published 2020-03-05
URL https://arxiv.org/abs/2003.02546v1
PDF https://arxiv.org/pdf/2003.02546v1.pdf
PWC https://paperswithcode.com/paper/embedding-expansion-augmentation-in-embedding

Selective Convolutional Network: An Efficient Object Detector with Ignoring Background

Title Selective Convolutional Network: An Efficient Object Detector with Ignoring Background
Authors Hefei Ling, Yangyang Qin, Li Zhang, Yuxuan Shi, Ping Li
Abstract It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt at attention. Therefore, we introduce an efficient object detector called Selective Convolutional Network (SCN), which selectively calculates only on the locations that contain meaningful and conducive information. The basic idea is to exclude the insignificant background areas, which effectively reduces the computational cost especially during the feature extraction. To solve it, we design an elaborate structure with negligible overheads to guide the network where to look next. It’s end-to-end trainable and easy-embedding. Without additional segmentation datasets, we explores two different train strategies including direct supervision and indirect supervision. Extensive experiments assess the performance on PASCAL VOC2007 and MS COCO detection datasets. Results show that SSD and Pelee integrated with our method averagely reduce the calculations in a range of 1/5 and 1/3 with slight loss of accuracy, demonstrating the feasibility of SCN.
Published 2020-02-04
URL https://arxiv.org/abs/2002.01205v1
PDF https://arxiv.org/pdf/2002.01205v1.pdf
PWC https://paperswithcode.com/paper/selective-convolutional-network-an-efficient

Deep OCT Angiography Image Generation for Motion Artifact Suppression

Title Deep OCT Angiography Image Generation for Motion Artifact Suppression
Authors Julian Hossbach, Lennart Husvogt, Martin F. Kraus, James G. Fujimoto, Andreas K. Maier
Abstract Eye movements, blinking and other motion during the acquisition of optical coherence tomography (OCT) can lead to artifacts, when processed to OCT angiography (OCTA) images. Affected scans emerge as high intensity (white) or missing (black) regions, resulting in lost information. The aim of this research is to fill these gaps using a deep generative model for OCT to OCTA image translation relying on a single intact OCT scan. Therefore, a U-Net is trained to extract the angiographic information from OCT patches. At inference, a detection algorithm finds outlier OCTA scans based on their surroundings, which are then replaced by the trained network. We show that generative models can augment the missing scans. The augmented volumes could then be used for 3-D segmentation or increase the diagnostic value.
Tasks Image Generation
Published 2020-01-08
URL https://arxiv.org/abs/2001.02512v1
PDF https://arxiv.org/pdf/2001.02512v1.pdf
PWC https://paperswithcode.com/paper/deep-oct-angiography-image-generation-for

SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation

Title SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation
Authors Mohsen Fayyaz, Juergen Gall
Abstract Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are only weakly labeled. In this work, we assume that for each training video only the list of actions is given that occur in the video, but not when, how often, and in which order they occur. In order to address this task, we propose an approach that can be trained end-to-end on such data. The approach divides the video into smaller temporal regions and predicts for each region the action label and its length. In addition, the network estimates the action labels for each frame. By measuring how consistent the frame-wise predictions are with respect to the temporal regions and the annotated action labels, the network learns to divide a video into class-consistent regions. We evaluate our approach on three datasets where the approach achieves state-of-the-art results.
Tasks action segmentation
Published 2020-03-31
URL https://arxiv.org/abs/2003.14266v1
PDF https://arxiv.org/pdf/2003.14266v1.pdf
PWC https://paperswithcode.com/paper/sct-set-constrained-temporal-transformer-for

Exact marginal inference in Latent Dirichlet Allocation

Title Exact marginal inference in Latent Dirichlet Allocation
Authors Hartmut Maennel
Abstract Assume we have potential “causes” $z\in Z$, which produce “events” $w$ with known probabilities $\beta(wz)$. We observe $w_1,w_2,…,w_n$, what can we say about the distribution of the causes? A Bayesian estimate will assume a prior on distributions on $Z$ (we assume a Dirichlet prior) and calculate a posterior. An average over that posterior then gives a distribution on $Z$, which estimates how much each cause $z$ contributed to our observations. This is the setting of Latent Dirichlet Allocation, which can be applied e.g. to topics “producing” words in a document. In this setting usually the number of observed words is large, but the number of potential topics is small. We are here interested in applications with many potential “causes” (e.g. locations on the globe), but only a few observations. We show that the exact Bayesian estimate can be computed in linear time (and constant space) in $Z$ for a given upper bound on $n$ with a surprisingly simple formula. We generalize this algorithm to the case of sparse probabilities $\beta(wz)$, in which we only need to assume that the tree width of an “interaction graph” on the observations is limited. On the other hand we also show that without such limitation the problem is NP-hard.
Published 2020-03-31
URL https://arxiv.org/abs/2004.00115v1
PDF https://arxiv.org/pdf/2004.00115v1.pdf
PWC https://paperswithcode.com/paper/exact-marginal-inference-in-latent-dirichlet
comments powered by Disqus