February 2, 2020

3339 words 16 mins read

Paper Group AWR 56

Fleet Prognosis with Physics-informed Recurrent Neural Networks. 3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation. Recognizing Manipulation Actions from State-Transformations. Forecasting remaining useful life: Interpretable deep learning approach via variational Bayesian inferences. Self-Paced Multi-Label Learning wit …

Fleet Prognosis with Physics-informed Recurrent Neural Networks


Title	Fleet Prognosis with Physics-informed Recurrent Neural Networks
Authors	Renato Giorgiani Nascimento, Felipe A. C. Viana
Abstract	Services and warranties of large fleets of engineering assets is a very profitable business. The success of companies in that area is often related to predictive maintenance driven by advanced analytics. Therefore, accurate modeling, as a way to understand how the complex interactions between operating conditions and component capability define useful life, is key for services profitability. Unfortunately, building prognosis models for large fleets is a daunting task as factors such as duty cycle variation, harsh environments, inadequate maintenance, and problems with mass production can lead to large discrepancies between designed and observed useful lives. This paper introduces a novel physics-informed neural network approach to prognosis by extending recurrent neural networks to cumulative damage models. We propose a new recurrent neural network cell designed to merge physics-informed and data-driven layers. With that, engineers and scientists have the chance to use physics-informed layers to model parts that are well understood (e.g., fatigue crack growth) and use data-driven layers to model parts that are poorly characterized (e.g., internal loads). A simple numerical experiment is used to present the main features of the proposed physics-informed recurrent neural network for damage accumulation. The test problem consist of predicting fatigue crack length for a synthetic fleet of airplanes subject to different mission mixes. The model is trained using full observation inputs (far-field loads) and very limited observation of outputs (crack length at inspection for only a portion of the fleet). The results demonstrate that our proposed hybrid physics-informed recurrent neural network is able to accurately model fatigue crack growth even when the observed distribution of crack length does not match with the (unobservable) fleet distribution.
Tasks
Published	2019-01-16
URL	http://arxiv.org/abs/1901.05512v1
PDF	http://arxiv.org/pdf/1901.05512v1.pdf
PWC	https://paperswithcode.com/paper/fleet-prognosis-with-physics-informed
Repo	https://github.com/PML-UCF/pinn
Framework	tf

3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation


Title	3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation
Authors	Chao Huang, Hu Han, Qingsong Yao, Shankuan Zhu, S. Kevin Zhou
Abstract	Fully convolutional neural networks like U-Net have been the state-of-the-art methods in medical image segmentation. Practically, a network is highly specialized and trained separately for each segmentation task. Instead of a collection of multiple models, it is highly desirable to learn a universal data representation for different tasks, ideally a single model with the addition of a minimal number of parameters steered to each task. Inspired by the recent success of multi-domain learning in image classification, for the first time we explore a promising universal architecture that handles multiple medical segmentation tasks and is extendable for new tasks, regardless of different organs and imaging modalities. Our 3D Universal U-Net (3D U$^2$-Net) is built upon separable convolution, assuming that {\it images from different domains have domain-specific spatial correlations which can be probed with channel-wise convolution while also share cross-channel correlations which can be modeled with pointwise convolution}. We evaluate the 3D U$^2$-Net on five organ segmentation datasets. Experimental results show that this universal network is capable of competing with traditional models in terms of segmentation accuracy, while requiring only about $1%$ of the parameters. Additionally, we observe that the architecture can be easily and effectively adapted to a new domain without sacrificing performance in the domains used to learn the shared parameterization of the universal network. We put the code of 3D U$^2$-Net into public domain. \url{https://github.com/huangmozhilv/u2net_torch/}
Tasks	Image Classification, Medical Image Segmentation, Semantic Segmentation
Published	2019-09-04
URL	https://arxiv.org/abs/1909.06012v1
PDF	https://arxiv.org/pdf/1909.06012v1.pdf
PWC	https://paperswithcode.com/paper/3d-u2-net-a-3d-universal-u-net-for-multi
Repo	https://github.com/huangmozhilv/u2net_torch
Framework	pytorch

Recognizing Manipulation Actions from State-Transformations


Title	Recognizing Manipulation Actions from State-Transformations
Authors	Nachwa Aboubakr, James L. Crowley, Remi Ronfard
Abstract	Manipulation actions transform objects from an initial state into a final state. In this paper, we report on the use of object state transitions as a mean for recognizing manipulation actions. Our method is inspired by the intuition that object states are visually more apparent than actions from a still frame and thus provide information that is complementary to spatio-temporal action recognition. We start by defining a state transition matrix that maps action labels into a pre-state and a post-state. From each keyframe, we learn appearance models of objects and their states. Manipulation actions can then be recognized from the state transition matrix. We report results on the EPIC kitchen action recognition challenge.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05147v1
PDF	https://arxiv.org/pdf/1906.05147v1.pdf
PWC	https://paperswithcode.com/paper/recognizing-manipulation-actions-from-state
Repo	https://github.com/Nachwa/object_states
Framework	pytorch

Forecasting remaining useful life: Interpretable deep learning approach via variational Bayesian inferences


Title	Forecasting remaining useful life: Interpretable deep learning approach via variational Bayesian inferences
Authors	Mathias Kraus, Stefan Feuerriegel
Abstract	Predicting the remaining useful life of machinery, infrastructure, or other equipment can facilitate preemptive maintenance decisions, whereby a failure is prevented through timely repair or replacement. This allows for a better decision support by considering the anticipated time-to-failure and thus promises to reduce costs. Here a common baseline may be derived by fitting a probability density function to past lifetimes and then utilizing the (conditional) expected remaining useful life as a prognostic. This approach finds widespread use in practice because of its high explanatory power. A more accurate alternative is promised by machine learning, where forecasts incorporate deterioration processes and environmental variables through sensor data. However, machine learning largely functions as a black-box method and its forecasts thus forfeit most of the desired interpretability. As our primary contribution, we propose a structured-effect neural network for predicting the remaining useful life which combines the favorable properties of both approaches: its key innovation is that it offers both a high accountability and the flexibility of deep learning. The parameters are estimated via variational Bayesian inferences. The different approaches are compared based on the actual time-to-failure for aircraft engines. This demonstrates the performance and superior interpretability of our method, while we finally discuss implications for decision support.
Tasks
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05146v2
PDF	https://arxiv.org/pdf/1907.05146v2.pdf
PWC	https://paperswithcode.com/paper/forecasting-remaining-useful-life
Repo	https://github.com/MathiasKraus/PredictiveMaintenance
Framework	pytorch

Self-Paced Multi-Label Learning with Diversity


Title	Self-Paced Multi-Label Learning with Diversity
Authors	Seyed Amjad Seyedi, S. Siamak Ghodsi, Fardin Akhlaghian, Mahdi Jalili, Parham Moradi
Abstract	The major challenge of learning from multi-label data has arisen from the overwhelming size of label space which makes this problem NP-hard. This problem can be alleviated by gradually involving easy to hard tags into the learning process. Besides, the utilization of a diversity maintenance approach avoids overfitting on a subset of easy labels. In this paper, we propose a self-paced multi-label learning with diversity (SPMLD) which aims to cover diverse labels with respect to its learning pace. In addition, the proposed framework is applied to an efficient correlation-based multi-label method. The non-convex objective function is optimized by an extension of the block coordinate descent algorithm. Empirical evaluations on real-world datasets with different dimensions of features and labels imply the effectiveness of the proposed predictive model.
Tasks	Multi-Label Learning
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03497v1
PDF	https://arxiv.org/pdf/1910.03497v1.pdf
PWC	https://paperswithcode.com/paper/self-paced-multi-label-learning-with
Repo	https://github.com/amjadseyedi/SPMLD
Framework	none

Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor Infiltrating Lymphocytes in Invasive Breast Cancer


Title	Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor Infiltrating Lymphocytes in Invasive Breast Cancer
Authors	Han Le, Rajarsi Gupta, Le Hou, Shahira Abousamra, Danielle Fassler, Tahsin Kurc, Dimitris Samaras, Rebecca Batiste, Tianhao Zhao, Arvind Rao, Alison L. Van Dyke, Ashish Sharma, Erich Bremer, Jonas S. Almeida, Joel Saltz
Abstract	Quantitative assessment of Tumor-TIL spatial relationships is increasingly important in both basic science and clinical aspects of breast cancer research. We have developed and evaluated convolutional neural network (CNN) analysis pipelines to generate combined maps of cancer regions and tumor infiltrating lymphocytes (TILs) in routine diagnostic breast cancer whole slide tissue images (WSIs). We produce interactive whole slide maps that provide 1) insight about the structural patterns and spatial distribution of lymphocytic infiltrates and 2) facilitate improved quantification of TILs. We evaluated both tumor and TIL analyses using three CNN networks - Resnet-34, VGG16 and Inception v4, and demonstrated that the results compared favorably to those obtained by what believe are the best published methods. We have produced open-source tools and generated a public dataset consisting of tumor/TIL maps for 1,015 TCGA breast cancer images. We also present a customized web-based interface that enables easy visualization and interactive exploration of high-resolution combined Tumor-TIL maps for 1,015TCGA invasive breast cancer cases that can be downloaded for further downstream analyses.
Tasks	Breast Cancer Detection
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10841v3
PDF	https://arxiv.org/pdf/1905.10841v3.pdf
PWC	https://paperswithcode.com/paper/utilizing-automated-breast-cancer-detection
Repo	https://github.com/SBU-BMI/quip_cancer_segmentation
Framework	pytorch

Asynchronous Federated Learning with Differential Privacy for Edge Intelligence


Title	Asynchronous Federated Learning with Differential Privacy for Edge Intelligence
Authors	Yanan Li, Shusen Yang, Xuebin Ren, Cong Zhao
Abstract	Federated learning has been showing as a promising approach in paving the last mile of artificial intelligence, due to its great potential of solving the data isolation problem in large scale machine learning. Particularly, with consideration of the heterogeneity in practical edge computing systems, asynchronous edge-cloud collaboration based federated learning can further improve the learning efficiency by significantly reducing the straggler effect. Despite no raw data sharing, the open architecture and extensive collaborations of asynchronous federated learning (AFL) still give some malicious participants great opportunities to infer other parties’ training data, thus leading to serious concerns of privacy. To achieve a rigorous privacy guarantee with high utility, we investigate to secure asynchronous edge-cloud collaborative federated learning with differential privacy, focusing on the impacts of differential privacy on model convergence of AFL. Formally, we give the first analysis on the model convergence of AFL under DP and propose a multi-stage adjustable private algorithm (MAPA) to improve the trade-off between model utility and privacy by dynamically adjusting both the noise scale and the learning rate. Through extensive simulations and real-world experiments with an edge-could testbed, we demonstrate that MAPA significantly improves both the model accuracy and convergence speed with sufficient privacy guarantee.
Tasks
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07902v1
PDF	https://arxiv.org/pdf/1912.07902v1.pdf
PWC	https://paperswithcode.com/paper/asynchronous-federated-learning-with
Repo	https://github.com/IoTDATALab/MAPA
Framework	pytorch

Edge-Informed Single Image Super-Resolution


Title	Edge-Informed Single Image Super-Resolution
Authors	Kamyar Nazeri, Harrish Thasarathan, Mehran Ebrahimi
Abstract	The recent increase in the extensive use of digital imaging technologies has brought with it a simultaneous demand for higher-resolution images. We develop a novel edge-informed approach to single image super-resolution (SISR). The SISR problem is reformulated as an image inpainting task. We use a two-stage inpainting model as a baseline for super-resolution and show its effectiveness for different scale factors (x2, x4, x8) compared to basic interpolation schemes. This model is trained using a joint optimization of image contents (texture and color) and structures (edges). Quantitative and qualitative comparisons are included and the proposed model is compared with current state-of-the-art techniques. We show that our method of decoupling structure and texture reconstruction improves the quality of the final reconstructed high-resolution image. Code and models available at: https://github.com/knazeri/edge-informed-sisr
Tasks	Image Inpainting, Image Super-Resolution, Super-Resolution
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05305v1
PDF	https://arxiv.org/pdf/1909.05305v1.pdf
PWC	https://paperswithcode.com/paper/edge-informed-single-image-super-resolution
Repo	https://github.com/knazeri/edge-informed-sisr
Framework	pytorch

Image anomaly detection with capsule networks and imbalanced datasets


Title	Image anomaly detection with capsule networks and imbalanced datasets
Authors	Claudio Piciarelli, Pankaj Mishra, Gian Luca Foresti
Abstract	Image anomaly detection consists in finding images with anomalous, unusual patterns with respect to a set of normal data. Anomaly detection can be applied to several fields and has numerous practical applications, e.g. in industrial inspection, medical imaging, security enforcement, etc.. However, anomaly detection techniques often still rely on traditional approaches such as one-class Support Vector Machines, while the topic has not been fully developed yet in the context of modern deep learning approaches. In this paper, we propose an image anomaly detection system based on capsule networks under the assumption that anomalous data are available for training but their amount is scarce.
Tasks	Anomaly Detection
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02755v1
PDF	https://arxiv.org/pdf/1909.02755v1.pdf
PWC	https://paperswithcode.com/paper/image-anomaly-detection-with-capsule-networks
Repo	https://github.com/bakirillov/capsules
Framework	pytorch

Story Realization: Expanding Plot Events into Sentences


Title	Story Realization: Expanding Plot Events into Sentences
Authors	Prithviraj Ammanabrolu, Ethan Tien, Wesley Cheung, Zhaochen Luo, William Ma, Lara J. Martin, Mark O. Riedl
Abstract	Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and (2) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events.We provide results—including a human subjects study—for a full end-to-end automated story generation system showing that our method generates more coherent and plausible stories than baseline approaches.
Tasks	Text Generation
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03480v2
PDF	https://arxiv.org/pdf/1909.03480v2.pdf
PWC	https://paperswithcode.com/paper/story-realization-expanding-plot-events-into
Repo	https://github.com/rajammanabrolu/StoryRealization
Framework	pytorch

Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems


Title	Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems
Authors	Ashwini Challa, Kartikeya Upasani, Anusha Balakrishnan, Rajen Subba
Abstract	Neural approaches to Natural Language Generation (NLG) have been promising for goal-oriented dialogue. One of the challenges of productionizing these approaches, however, is the ability to control response quality, and ensure that generated responses are acceptable. We propose the use of a generate, filter, and rank framework, in which candidate responses are first filtered to eliminate unacceptable responses, and then ranked to select the best response. While acceptability includes grammatical correctness and semantic correctness, we focus only on grammaticality classification in this paper, and show that existing datasets for grammatical error correction don’t correctly capture the distribution of errors that data-driven generators are likely to make. We release a grammatical classification and semantic correctness classification dataset for the weather domain that consists of responses generated by 3 data-driven NLG systems. We then explore two supervised learning approaches (CNNs and GBDTs) for classifying grammaticality. Our experiments show that grammaticality classification is very sensitive to the distribution of errors in the data, and that these distributions vary significantly with both the source of the response as well as the domain. We show that it’s possible to achieve high precision with reasonable recall on our dataset.
Tasks	Grammatical Error Correction, Text Generation
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03279v2
PDF	http://arxiv.org/pdf/1904.03279v2.pdf
PWC	https://paperswithcode.com/paper/generate-filter-and-rank-grammaticality
Repo	https://github.com/facebookresearch/momi
Framework	none

Latent Multi-view Semi-Supervised Classification


Title	Latent Multi-view Semi-Supervised Classification
Authors	Xiaofan Bo, Zhao Kang, Zhitong Zhao, Yuanzhang Su, Wenyu Chen
Abstract	To explore underlying complementary information from multiple views, in this paper, we propose a novel Latent Multi-view Semi-Supervised Classification (LMSSC) method. Unlike most existing multi-view semi-supervised classification methods that learn the graph using original features, our method seeks an underlying latent representation and performs graph learning and label propagation based on the learned latent representation. With the complementarity of multiple views, the latent representation could depict the data more comprehensively than every single view individually, accordingly making the graph more accurate and robust as well. Finally, LMSSC integrates latent representation learning, graph construction, and label propagation into a unified framework, which makes each subtask optimized. Experimental results on real-world benchmark datasets validate the effectiveness of our proposed method.
Tasks	graph construction, Representation Learning
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03712v1
PDF	https://arxiv.org/pdf/1909.03712v1.pdf
PWC	https://paperswithcode.com/paper/latent-multi-view-semi-supervised
Repo	https://github.com/sckangz/LMVL
Framework	none

Read, Highlight and Summarize: A Hierarchical Neural Semantic Encoder-based Approach


Title	Read, Highlight and Summarize: A Hierarchical Neural Semantic Encoder-based Approach
Authors	Rajeev Bhatt Ambati, Saptarashmi Bandyopadhyay, Prasenjit Mitra
Abstract	Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way humans use language by forming paragraphs from sentences and sentences from words, hierarchical models have usually not worked that much better than their traditional seq2seq counterparts. This effect is mainly because either the hierarchical attention mechanisms are too sparse using hard attention or noisy using soft attention. In this paper, we propose a method based on extracting the highlights of a document; a key concept that is conveyed in a few sentences. In a typical text summarization dataset consisting of documents that are 800 tokens in length (average), capturing long-term dependencies is very important, e.g., the last sentence can be grouped with the first sentence of a document to form a summary. LSTMs (Long Short-Term Memory) proved useful for machine translation. However, they often fail to capture long-term dependencies while modeling long sequences. To address these issues, we have adapted Neural Semantic Encoders (NSE) to text summarization, a class of memory-augmented neural networks by improving its functionalities and proposed a novel hierarchical NSE that outperforms similar previous models significantly. The quality of summarization was improved by augmenting linguistic factors, namely lemma, and Part-of-Speech (PoS) tags, to each word in the dataset for improved vocabulary coverage and generalization. The hierarchical NSE model on factored dataset outperformed the state-of-the-art by nearly 4 ROUGE points. We further designed and used the first GPU-based self-critical Reinforcement Learning model.
Tasks	Abstractive Text Summarization, Machine Translation, Text Summarization
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03177v2
PDF	https://arxiv.org/pdf/1910.03177v2.pdf
PWC	https://paperswithcode.com/paper/read-highlight-and-summarize-a-hierarchical
Repo	https://github.com/rajeev595/RHS_HierNSE
Framework	tf

Predicting with High Correlation Features


Title	Predicting with High Correlation Features
Authors	Devansh Arpit, Caiming Xiong, Richard Socher
Abstract	It has been shown that instead of learning actual object features, deep networks tend to exploit non-robust (spurious) discriminative features that are shared between training and test sets. Therefore, while they achieve state of the art performance on such test sets, they achieve poor generalization on out of distribution (OOD) samples where the IID (independent, identical distribution) assumption breaks and the distribution of non-robust features shifts. In this paper, we consider distribution shift as a shift in the distribution of input features during test time that exhibit low correlation with targets in the training set. Under this definition, we evaluate existing robust feature learning methods and regularization methods and compare them against a baseline designed to specifically capture high correlation features in training set. As a controlled test-bed, we design a colored MNIST (C-MNIST) dataset and find that existing methods trained on this set fail to generalize well on an OOD version this dataset, showing that they overfit the low correlation color features. This is avoided by the baseline method trained on the same C-MNIST data, which is designed to learn high correlation features, and is able to generalize on the test sets of vanilla MNIST, MNIST-M and SVHN datasets. Our code is available at \url{https://github.com/salesforce/corr_based_prediction}.
Tasks
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00164v2
PDF	https://arxiv.org/pdf/1910.00164v2.pdf
PWC	https://paperswithcode.com/paper/entropy-penalty-towards-generalization-beyond
Repo	https://github.com/salesforce/EntropyPenalty
Framework	pytorch

Morphological Networks for Image De-raining


Title	Morphological Networks for Image De-raining
Authors	Ranjan Mondal, Pulak Purkait, Sanchayan Santra, Bhabatosh Chanda
Abstract	Mathematical morphological methods have successfully been applied to filter out (emphasize or remove) different structures of an image. However, it is argued that these methods could be suitable for the task only if the type and order of the filter(s) as well as the shape and size of operator kernel are designed properly. Thus the existing filtering operators are problem (instance) specific and are designed by the domain experts. In this work we propose a morphological network that emulates classical morphological filtering consisting of a series of erosion and dilation operators with trainable structuring elements. We evaluate the proposed network for image de-raining task where the SSIM and mean absolute error (MAE) loss corresponding to predicted and ground-truth clean image is back-propagated through the network to train the structuring elements. We observe that a single morphological network can de-rain an image with any arbitrary shaped rain-droplets and achieves similar performance with the contemporary CNNs for this task with a fraction of trainable parameters (network size). The proposed morphological network(MorphoN) is not designed specifically for de-raining and can readily be applied to similar filtering / noise cleaning tasks. The source code can be found here https://github.com/ranjanZ/2D-Morphological-Network
Tasks
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02411v1
PDF	http://arxiv.org/pdf/1901.02411v1.pdf
PWC	https://paperswithcode.com/paper/morphological-networks-for-image-de-raining
Repo	https://github.com/ranjanZ/2D-Morphological-Network
Framework	tf