January 27, 2020

2955 words 14 mins read

Paper Group ANR 1291

Posing Fair Generalization Tasks for Natural Language Inference. A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages. A clusterwise supervised learning procedure based on aggregation of distances. Does Object Recognition Work for Everyone?. Face Detection and Face Recognition In the Wild Using Off-the-She …

Posing Fair Generalization Tasks for Natural Language Inference


Title	Posing Fair Generalization Tasks for Natural Language Inference
Authors	Atticus Geiger, Ignacio Cases, Lauri Karttunen, Chris Potts
Abstract	Deep learning models for semantics are generally evaluated using naturalistic corpora. Adversarial methods, in which models are evaluated on new examples with known semantic properties, have begun to reveal that good performance at these naturalistic tasks can hide serious shortcomings. However, we should insist that these evaluations be fair -that the models are given data sufficient to support the requisite kinds of generalization. In this paper, we define and motivate a formal notion of fairness in this sense. We then apply these ideas to natural language inference by constructing very challenging but provably fair artificial datasets and showing that standard neural models fail to generalize in the required ways; only task-specific models that jointly compose the premise and hypothesis are able to achieve high performance, and even these models do not solve the task perfectly.
Tasks	Natural Language Inference
Published	2019-11-03
URL	https://arxiv.org/abs/1911.00811v1
PDF	https://arxiv.org/pdf/1911.00811v1.pdf
PWC	https://paperswithcode.com/paper/posing-fair-generalization-tasks-for-natural-1
Repo
Framework

A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages


Title	A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages
Authors	Minh-Thang Luong, Preslav Nakov, Min-Yen Kan
Abstract	We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process. Our model extends the classic phrase-based model by means of (1) word boundary-aware morpheme-level phrase extraction, (2) minimum error-rate training for a morpheme-level translation model using word-level BLEU, and (3) joint scoring with morpheme- and word-level language models. Further improvements are achieved by combining our model with the classic one. The evaluation on English to Finnish using Europarl (714K sentence pairs; 15.5M English words) shows statistically significant improvements over the classic model based on BLEU and human judgments.
Tasks	Machine Translation
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08117v1
PDF	https://arxiv.org/pdf/1911.08117v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-morpheme-word-representation-for
Repo
Framework

A clusterwise supervised learning procedure based on aggregation of distances


Title	A clusterwise supervised learning procedure based on aggregation of distances
Authors	Aurélie Fisher, Mathilde Mougeot, Sothea Has
Abstract	Nowadays, many machine learning procedures are available on the shelve and may be used easily to calibrate predictive models on supervised data. However, when the input data consists of more than one unknown cluster, and when different underlying predictive models exist, fitting a model is a more challenging task. We propose, in this paper, a procedure in three steps to automatically solve this problem. The KFC procedure aggregates different models adaptively on data. The first step of the procedure aims at catching the clustering structure of the input data, which may be characterized by several statistical distributions. It provides several partitions, given the assumptions on the distributions. For each partition, the second step fits a specific predictive model based on the data in each cluster. The overall model is computed by a consensual aggregation of the models corresponding to the different partitions. A comparison of the performances on different simulated and real data assesses the excellent performance of our method in a large variety of prediction problems.
Tasks
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09370v3
PDF	https://arxiv.org/pdf/1909.09370v3.pdf
PWC	https://paperswithcode.com/paper/consensual-aggregation-of-clusters-based-on
Repo
Framework

Does Object Recognition Work for Everyone?


Title	Does Object Recognition Work for Everyone?
Authors	Terrance DeVries, Ishan Misra, Changhan Wang, Laurens van der Maaten
Abstract	The paper analyzes the accuracy of publicly available object-recognition systems on a geographically diverse dataset. This dataset contains household items and was designed to have a more representative geographical coverage than commonly used image datasets in object recognition. We find that the systems perform relatively poorly on household items that commonly occur in countries with a low household income. Qualitative analyses suggest the drop in performance is primarily due to appearance differences within an object class (e.g., dish soap) and due to items appearing in a different context (e.g., toothbrushes appearing outside of bathrooms). The results of our study suggest that further work is needed to make object-recognition systems work equally well for people across different countries and income levels.
Tasks	Object Recognition
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02659v2
PDF	https://arxiv.org/pdf/1906.02659v2.pdf
PWC	https://paperswithcode.com/paper/does-object-recognition-work-for-everyone
Repo
Framework

Face Detection and Face Recognition In the Wild Using Off-the-Shelf Freely Available Components


Title	Face Detection and Face Recognition In the Wild Using Off-the-Shelf Freely Available Components
Authors	Hira Ahmad
Abstract	This paper presents an easy and efficient face detection and face recognition approach using free software components from the internet. Face detection and face recognition problems have wide applications in home and office security. Therefore this work will helpful for those searching for a free face off-the-shelf face detection system. Using this system, faces can be detected in uncontrolled environments. In the detection phase, every individual face is detected and in the recognition phase the detected faces are compared with the faces in a given data set and recognized.
Tasks	Face Detection, Face Recognition
Published	2019-01-19
URL	http://arxiv.org/abs/1901.06585v1
PDF	http://arxiv.org/pdf/1901.06585v1.pdf
PWC	https://paperswithcode.com/paper/face-detection-and-face-recognition-in-the
Repo
Framework

Multi-task Localization and Segmentation for X-ray Guided Planning in Knee Surgery


Title	Multi-task Localization and Segmentation for X-ray Guided Planning in Knee Surgery
Authors	Florian Kordon, Peter Fischer, Maxim Privalov, Benedict Swartman, Marc Schnetzke, Jochen Franke, Ruxandra Lasowski, Andreas Maier, Holger Kunze
Abstract	X-ray based measurement and guidance are commonly used tools in orthopaedic surgery to facilitate a minimally invasive workflow. Typically, a surgical planning is first performed using knowledge of bone morphology and anatomical landmarks. Information about bone location then serves as a prior for registration during overlay of the planning on intra-operative X-ray images. Performing these steps manually however is prone to intra-rater/inter-rater variability and increases task complexity for the surgeon. To remedy these issues, we propose an automatic framework for planning and subsequent overlay. We evaluate it on the example of femoral drill site planning for medial patellofemoral ligament reconstruction surgery. A deep multi-task stacked hourglass network is trained on 149 conventional lateral X-ray images to jointly localize two femoral landmarks, to predict a region of interest for the posterior femoral cortex tangent line, and to perform semantic segmentation of the femur, patella, tibia, and fibula with adaptive task complexity weighting. On 38 clinical test images the framework achieves a median localization error of 1.50 mm for the femoral drill site and mean IOU scores of 0.99, 0.97, 0.98, and 0.96 for the femur, patella, tibia, and fibula respectively. The demonstrated approach consistently performs surgical planning at expert-level precision without the need for manual correction.
Tasks	Semantic Segmentation
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10465v1
PDF	https://arxiv.org/pdf/1907.10465v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-localization-and-segmentation-for
Repo
Framework

Augmenting Model Robustness with Transformation-Invariant Attacks


Title	Augmenting Model Robustness with Transformation-Invariant Attacks
Authors	Houpu Yao, Zhe Wang, Guangyu Nie, Yassine Mazboudi, Yezhou Yang, Yi Ren
Abstract	The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensitive to input transformations such as linear translation and rotation, and that human vision, which is robust against adversarial attacks, is invariant to natural input transformations. Based on these, this paper tests the hypothesis that model robustness can be further improved when it is adversarially trained against transformed attacks and transformation-invariant attacks. Experiments on MNIST, CIFAR-10, and restricted ImageNet show that while transformations of attacks alone do not affect robustness, transformation-invariant attacks can improve model robustness by 2.5% on MNIST, 3.7% on CIFAR-10, and 1.1% on restricted ImageNet. We discuss the intuition behind this phenomenon.
Tasks	Image Cropping
Published	2019-01-31
URL	https://arxiv.org/abs/1901.11188v2
PDF	https://arxiv.org/pdf/1901.11188v2.pdf
PWC	https://paperswithcode.com/paper/improving-model-robustness-with
Repo
Framework

Split Learning for collaborative deep learning in healthcare


Title	Split Learning for collaborative deep learning in healthcare
Authors	Maarten G. Poirot, Praneeth Vepakomma, Ken Chang, Jayashree Kalpathy-Cramer, Rajiv Gupta, Ramesh Raskar
Abstract	Shortage of labeled data has been holding the surge of deep learning in healthcare back, as sample sizes are often small, patient information cannot be shared openly, and multi-center collaborative studies are a burden to set up. Distributed machine learning methods promise to mitigate these problems. We argue for a split learning based approach and apply this distributed learning method for the first time in the medical field to compare performance against (1) centrally hosted and (2) non collaborative configurations for a range of participants. Two medical deep learning tasks are used to compare split learning to conventional single and multi center approaches: a binary classification problem of a data set of 9000 fundus photos, and multi-label classification problem of a data set of 156,535 chest X-rays. The several distributed learning setups are compared for a range of 1-50 distributed participants. Performance of the split learning configuration remained constant for any number of clients compared to a single center study, showing a marked difference compared to the non collaborative configuration after 2 clients (p < 0.001) for both sets. Our results affirm the benefits of collaborative training of deep neural networks in health care. Our work proves the significant benefit of distributed learning in healthcare, and paves the way for future real-world implementations.
Tasks	Multi-Label Classification
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12115v1
PDF	https://arxiv.org/pdf/1912.12115v1.pdf
PWC	https://paperswithcode.com/paper/split-learning-for-collaborative-deep
Repo
Framework

Designing an AI Health Coach and Studying its Utility in Promoting Regular Aerobic Exercise


Title	Designing an AI Health Coach and Studying its Utility in Promoting Regular Aerobic Exercise
Authors	Shiwali Mohan, Anusha Venkatakrishnan, Andrea Hartzler
Abstract	Our research aims to develop interactive, social agents that can coach people to learn new tasks, skills, and habits. In this paper, we focus on coaching sedentary, overweight individuals (i.e., trainees) to exercise regularly. We employ adaptive goal setting in which the intelligent health coach generates, tracks, and revises personalized exercise goals for a trainee. The goals become incrementally more difficult as the trainee progresses through the training program. Our approach is model-based - the coach maintains a parameterized model of the trainee’s aerobic capability that drives its expectation of the trainee’s performance. The model is continually revised based on trainee-coach interactions. The coach is embodied in a smartphone application, NutriWalking, which serves as a medium for coach-trainee interaction. We adopt a task-centric evaluation approach for studying the utility of the proposed algorithm in promoting regular aerobic exercise. We show that our approach can adapt the trainee program not only to several trainees with different capabilities, but also to how a trainee’s capability improves as they begin to exercise more. Experts rate the goals selected by the coach better than other plausible goals, demonstrating that our approach is consistent with clinical recommendations. Further, in a 6-week observational study with sedentary participants, we show that the proposed approach helps increase exercise volume performed each week.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04836v1
PDF	https://arxiv.org/pdf/1910.04836v1.pdf
PWC	https://paperswithcode.com/paper/designing-an-ai-health-coach-and-studying-its
Repo
Framework

Global optimization of dielectric metasurfaces using a physics-driven neural network


Title	Global optimization of dielectric metasurfaces using a physics-driven neural network
Authors	Jiaqi Jiang, Jonathan A. Fan
Abstract	We present a global optimizer, based on a conditional generative neural network, which can output ensembles of highly efficient topology-optimized metasurfaces operating across a range of parameters. A key feature of the network is that it initially generates a distribution of devices that broadly samples the design space, and then shifts and refines this distribution towards favorable design space regions over the course of optimization. Training is performed by calculating the forward and adjoint electromagnetic simulations of outputted devices and using the subsequent efficiency gradients for backpropagation. With metagratings operating across a range of wavelengths and angles as a model system, we show that devices produced from the trained generative network have efficiencies comparable to or better than the best devices produced by adjoint-based topology optimization, while requiring less computational cost. Our reframing of adjoint-based optimization to the training of a generative neural network applies generally to physical systems that can utilize gradients to improve performance.
Tasks
Published	2019-05-13
URL	https://arxiv.org/abs/1906.04157v2
PDF	https://arxiv.org/pdf/1906.04157v2.pdf
PWC	https://paperswithcode.com/paper/global-optimization-of-dielectric
Repo
Framework

Application of Machine Learning to accidents detection at directional drilling


Title	Application of Machine Learning to accidents detection at directional drilling
Authors	Ekaterina Gurina, Nikita Klyuchnikov, Alexey Zaytsev, Evgenya Romanenkova, Ksenia Antipova, Igor Simon, Victor Makarov, Dmitry Koroteev
Abstract	We present a data-driven algorithm and mathematical model for anomaly alarming at directional drilling. The algorithm is based on machine learning. It compares the real-time drilling telemetry with one corresponding to past accidents and analyses the level of similarity. The model performs a time-series comparison using aggregated statistics and Gradient Boosting classification. It is trained on historical data containing the drilling telemetry of $80$ wells drilled within $19$ oilfields. The model can detect an anomaly and identify its type by comparing the real-time measurements while drilling with the ones from the database of past accidents. Validation tests show that our algorithm identifies half of the anomalies with about $0.53$ false alarms per day on average. The model performance ensures sufficient time and cost savings as it enables partial prevention of the failures and accidents at the well construction.
Tasks	Time Series
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02667v2
PDF	https://arxiv.org/pdf/1906.02667v2.pdf
PWC	https://paperswithcode.com/paper/failures-detection-at-directional-drilling
Repo
Framework

Red blood cell image generation for data augmentation using Conditional Generative Adversarial Networks


Title	Red blood cell image generation for data augmentation using Conditional Generative Adversarial Networks
Authors	Oleksandr Bailo, DongShik Ham, Young Min Shin
Abstract	In this paper, we describe how to apply image-to-image translation techniques to medical blood smear data to generate new data samples and meaningfully increase small datasets. Specifically, given the segmentation mask of the microscopy image, we are able to generate photorealistic images of blood cells which are further used alongside real data during the network training for segmentation and object detection tasks. This image data generation approach is based on conditional generative adversarial networks which have proven capabilities to high-quality image synthesis. In addition to synthesizing blood images, we synthesize segmentation mask as well which leads to a diverse variety of generated samples. The effectiveness of the technique is thoroughly analyzed and quantified through a number of experiments on a manually collected and annotated dataset of blood smear taken under a microscope.
Tasks	Data Augmentation, Image Generation, Image-to-Image Translation, Object Detection
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06219v2
PDF	http://arxiv.org/pdf/1901.06219v2.pdf
PWC	https://paperswithcode.com/paper/red-blood-cell-image-generation-for-data
Repo
Framework

Deep Likelihood Network for Image Restoration with Multiple Degradation Levels


Title	Deep Likelihood Network for Image Restoration with Multiple Degradation Levels
Authors	Yiwen Guo, Ming Lu, Wangmeng Zuo, Changshui Zhang, Yurong Chen
Abstract	Convolutional neural networks have been proven very effective in a variety of image restoration tasks. Most state-of-the-art solutions, however, are trained using images with a single particular degradation level, and can deteriorate drastically when being applied to some other degradation settings. In this paper, we propose a novel method dubbed deep likelihood network (DL-Net), aiming at generalizing off-the-shelf image restoration networks to succeed over a spectrum of degradation settings while keeping their original learning objectives and core architectures. In particular, we slightly modify the original restoration networks by appending a simple yet effective recursive module, which is derived from a fidelity term for disentangling the effect of degradations. Extensive experimental results on image inpainting, interpolation and super-resolution demonstrate the effectiveness of our DL-Net.
Tasks	Image Inpainting, Image Restoration, Super-Resolution
Published	2019-04-19
URL	https://arxiv.org/abs/1904.09105v3
PDF	https://arxiv.org/pdf/1904.09105v3.pdf
PWC	https://paperswithcode.com/paper/deep-likelihood-network-for-image-restoration
Repo
Framework

AUC: Nonparametric Estimators and Their Smoothness


Title	AUC: Nonparametric Estimators and Their Smoothness
Authors	Waleed A. Yousef
Abstract	Nonparametric estimation of a statistic, in general, and of the error rate of a classification rule, in particular, from just one available dataset through resampling is well mathematically founded in the literature using several versions of bootstrap and influence function. This article first provides a concise review of this literature to establish the theoretical framework that we use to construct, in a single coherent framework, nonparametric estimators of the AUC (a two-sample statistic) other than the error rate (a one-sample statistic). In addition, the smoothness of some of these estimators is well investigated and explained. Our experiments show that the behavior of the designed AUC estimators confirms the findings of the literature for the behavior of error rate estimators in many aspects including: the weak correlation between the bootstrap-based estimators and the true conditional AUC; and the comparable accuracy of the different versions of the bootstrap estimators in terms of the RMS with little superiority of the .632+ bootstrap estimator.
Tasks
Published	2019-07-30
URL	https://arxiv.org/abs/1907.12851v1
PDF	https://arxiv.org/pdf/1907.12851v1.pdf
PWC	https://paperswithcode.com/paper/auc-nonparametric-estimators-and-their
Repo
Framework

CrossNet: Latent Cross-Consistency for Unpaired Image Translation


Title	CrossNet: Latent Cross-Consistency for Unpaired Image Translation
Authors	Omry Sendik, Dani Lischinski, Daniel Cohen-Or
Abstract	Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation. In particular, it was shown that a wide variety of image translation operators may be learned from two image sets, containing images from two different domains, without establishing an explicit pairing between the images. This was made possible by introducing clever regularizers to overcome the under-constrained nature of the unpaired translation problem. In this work, we introduce a novel architecture for unpaired image translation, and explore several new regularizers enabled by it. Specifically, our architecture comprises a pair of GANs, as well as a pair of translators between their respective latent spaces. These cross-translators enable us to impose several regularizing constraints on the learnt image translation operator, collectively referred to as latent cross-consistency. Our results show that our proposed architecture and latent cross-consistency constraints are able to outperform the existing state-of-the-art on a variety of image translation tasks.
Tasks	Image-to-Image Translation
Published	2019-01-14
URL	https://arxiv.org/abs/1901.04530v2
PDF	https://arxiv.org/pdf/1901.04530v2.pdf
PWC	https://paperswithcode.com/paper/xnet-gan-latent-space-constraints
Repo
Framework