January 30, 2020

2998 words 15 mins read

Paper Group ANR 234

Blind Geometric Distortion Correction on Images Through Deep Learning. Improving One-shot NAS by Suppressing the Posterior Fading. Semi-Supervised Semantic Matching. Synthesis of Realistic ECG using Generative Adversarial Networks. Towards Content Transfer through Grounded Text Generation. An Update on Machine Learning in Neuro-oncology Diagnostics …


Title	Blind Geometric Distortion Correction on Images Through Deep Learning
Authors	Xiaoyu Li, Bo Zhang, Pedro V. Sander, Jing Liao
Abstract	We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion dataset to predict the displacement field between distorted images and corrected images. A model fitting method uses the CNN output to estimate the distortion parameters, achieving a more accurate prediction. The final corrected image is generated based on the predicted flow using an efficient, high-quality resampling method. Experimental results demonstrate that our algorithm outperforms traditional correction methods, and allows for interesting applications such as distortion transfer, distortion exaggeration, and co-occurring distortion correction.
Tasks
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03459v1
PDF	https://arxiv.org/pdf/1909.03459v1.pdf
PWC	https://paperswithcode.com/paper/blind-geometric-distortion-correction-on-1
Repo
Framework

Improving One-shot NAS by Suppressing the Posterior Fading


Title	Improving One-shot NAS by Suppressing the Posterior Fading
Authors	Xiang Li, Chen Lin, Chuming Li, Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang
Abstract	There is a growing interest in automated neural architecture search (NAS). To improve the efficiency of NAS, previous approaches adopt weight sharing method to force all models share the same set of weights. However, it has been observed that a model performing better with shared weights does not necessarily perform better when trained alone. In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the posterior fading problem, which compromises the effectiveness of shared weights. To alleviate this problem, we present a practical approach to guide the parameter posterior towards its true distribution. Moreover, a hard latency constraint is introduced during the search so that the desired latency can be achieved. The resulted method, namely Posterior Convergent NAS (PC-NAS), achieves state-of-the-art performance under standard GPU latency constraint on ImageNet. In our small search space, our model PC-NAS-S attains 76.8 % top-1 accuracy, 2.1% higher than MobileNetV2 (1.4x) with the same latency. When adopted to the large search space, PC-NAS-L achieves 78.1 % top-1 accuracy within 11ms. The discovered architecture also transfers well to other computer vision applications such as object detection and person re-identification.
Tasks	Neural Architecture Search, Object Detection, Person Re-Identification
Published	2019-10-06
URL	https://arxiv.org/abs/1910.02543v1
PDF	https://arxiv.org/pdf/1910.02543v1.pdf
PWC	https://paperswithcode.com/paper/improving-one-shot-nas-by-suppressing-the
Repo
Framework

Semi-Supervised Semantic Matching


Title	Semi-Supervised Semantic Matching
Authors	Zakaria Laskar, Juho Kannala
Abstract	Convolutional neural networks (CNNs) have been successfully applied to solve the problem of correspondence estimation between semantically related images. Due to non-availability of large training datasets, existing methods resort to self-supervised or unsupervised training paradigm. In this paper we propose a semi-supervised learning framework that imposes cyclic consistency constraint on unlabeled image pairs. Together with the supervised loss the proposed model achieves state-of-the-art on a benchmark semantic matching dataset.
Tasks
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08339v1
PDF	http://arxiv.org/pdf/1901.08339v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-semantic-matching
Repo
Framework

Synthesis of Realistic ECG using Generative Adversarial Networks


Title	Synthesis of Realistic ECG using Generative Adversarial Networks
Authors	Anne Marie Delaney, Eoin Brophy, Tomas E. Ward
Abstract	Access to medical data is highly restricted due to its sensitive nature, preventing communities from using this data for research or clinical training. Common methods of de-identification implemented to enable the sharing of data are sometimes inadequate to protect the individuals contained in the data. For our research, we investigate the ability of generative adversarial networks (GANs) to produce realistic medical time series data which can be used without concerns over privacy. The aim is to generate synthetic ECG signals representative of normal ECG waveforms. GANs have been used successfully to generate good quality synthetic time series and have been shown to prevent re-identification of individual records. In this work, a range of GAN architectures are developed to generate synthetic sine waves and synthetic ECG. Two evaluation metrics are then used to quantitatively assess how suitable the synthetic data is for real world applications such as clinical training and data analysis. Finally, we discuss the privacy concerns associated with sharing synthetic data produced by GANs and test their ability to withstand a simple membership inference attack. For the first time we both quantitatively and qualitatively demonstrate that GAN architecture can successfully generate time series signals that are not only structurally similar to the training sets but also diverse in nature across generated samples. We also report on their ability to withstand a simple membership inference attack, protecting the privacy of the training set.
Tasks	Inference Attack, Time Series
Published	2019-09-19
URL	https://arxiv.org/abs/1909.09150v1
PDF	https://arxiv.org/pdf/1909.09150v1.pdf
PWC	https://paperswithcode.com/paper/synthesis-of-realistic-ecg-using-generative
Repo
Framework

Towards Content Transfer through Grounded Text Generation


Title	Towards Content Transfer through Grounded Text Generation
Authors	Shrimai Prabhumoye, Chris Quirk, Michel Galley
Abstract	Recent work in neural generation has attracted significant interest in controlling the form of text, such as style, persona, and politeness. However, there has been less work on controlling neural text generation for content. This paper introduces the notion of Content Transfer for long-form text generation, where the task is to generate a next sentence in a document that both fits its context and is grounded in a content-rich external textual source such as a news story. Our experiments on Wikipedia data show significant improvements against competitive baselines. As another contribution of this paper, we release a benchmark dataset of 640k Wikipedia referenced sentences paired with the source articles to encourage exploration of this new task.
Tasks	Text Generation
Published	2019-05-13
URL	https://arxiv.org/abs/1905.05293v1
PDF	https://arxiv.org/pdf/1905.05293v1.pdf
PWC	https://paperswithcode.com/paper/towards-content-transfer-through-grounded
Repo
Framework

An Update on Machine Learning in Neuro-oncology Diagnostics


Title	An Update on Machine Learning in Neuro-oncology Diagnostics
Authors	Thomas Booth
Abstract	Imaging biomarkers in neuro-oncology are used for diagnosis, prognosis and treatment response monitoring. Magnetic resonance imaging is typically used throughout the patient pathway because routine structural imaging provides detailed anatomical and pathological information and advanced techniques provide additional physiological detail. Following image feature extraction, machine learning allows accurate classification in a variety of scenarios. Machine learning also enables image feature extraction de novo although the low prevalence of brain tumours makes such approaches challenging. Much research is applied to determining molecular profiles, histological tumour grade and prognosis at the time that patients first present with a brain tumour. Following treatment, differentiating a treatment response from a post-treatment related effect is clinically important and also an area of study. Most of the evidence is low level having been obtained retrospectively and in single centres.
Tasks
Published	2019-08-09
URL	https://arxiv.org/abs/1910.08157v1
PDF	https://arxiv.org/pdf/1910.08157v1.pdf
PWC	https://paperswithcode.com/paper/an-update-on-machine-learning-in-neuro
Repo
Framework

Fully Automated Image De-fencing using Conditional Generative Adversarial Networks


Title	Fully Automated Image De-fencing using Conditional Generative Adversarial Networks
Authors	Divyanshu Gupta, Shorya Jain, Utkarsh Tripathi, Pratik Chattopadhyay, Lipo Wang
Abstract	Image de-fencing is one of the important aspects of recreational photography in which the objective is to remove the fence texture present in an image and generate an aesthetically pleasing version of the same image without the fence texture. In this paper, we aim to develop an automated and effective technique for fence removal and image reconstruction using conditional Generative Adversarial Networks (cGANs). These networks have been successfully applied in several domains of Computer Vision focusing on image generation and rendering. Our initial approach is based on a two-stage architecture involving two cGANs that generate the fence mask and the inpainted image, respectively. Training of these networks is carried out independently and, during evaluation, the input image is passed through the two generators in succession to obtain the de-fenced image. The results obtained from this approach are satisfactory, but the response time is long since the image has to pass through two sets of convolution layers. To reduce the response time, we propose a second approach involving only a single cGAN architecture that is trained using the ground-truth of fenced de-fenced image pairs along with the edge map of the fenced image produced by the Canny Filter. Incorporation of the edge map helps the network to precisely detect the edges present in the input image, and also imparts it an ability to carry out high quality de-fencing in an efficient manner, even in the presence of a fewer number of layers as compared to the two-stage network. Qualitative and quantitative experimental results reported in the manuscript reveal that the de-fenced images generated by the single-stage de-fencing network have similar visual quality to those produced by the two-stage network. Comparative performance analysis also emphasizes the effectiveness of our approach over state-of-the-art image de-fencing techniques.
Tasks	Image Generation, Image Reconstruction
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06837v1
PDF	https://arxiv.org/pdf/1908.06837v1.pdf
PWC	https://paperswithcode.com/paper/fully-automated-image-de-fencing-using
Repo
Framework

Right-wing German Hate Speech on Twitter: Analysis and Automatic Detection


Title	Right-wing German Hate Speech on Twitter: Analysis and Automatic Detection
Authors	Sylvia Jaki, Tom De Smedt
Abstract	Discussion about the social network Twitter often concerns its role in political discourse, involving the question of when an expression of opinion becomes offensive, immoral, and/or illegal, and how to deal with it. Given the growing amount of offensive communication on the internet, there is a demand for new technology that can automatically detect hate speech, to assist content moderation by humans. This comes with new challenges, such as defining exactly what is free speech and what is illegal in a specific country, and knowing exactly what the linguistic characteristics of hate speech are. To shed light on the German situation, we analyzed over 50,000 right-wing German hate tweets posted between August 2017 and April 2018, at the time of the 2017 German federal elections, using both quantitative and qualitative methods. In this paper, we discuss the results of the analysis and demonstrate how the insights can be employed for the development of automatic detection systems.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07518v1
PDF	https://arxiv.org/pdf/1910.07518v1.pdf
PWC	https://paperswithcode.com/paper/right-wing-german-hate-speech-on-twitter
Repo
Framework

Identifying the Most Explainable Classifier


Title	Identifying the Most Explainable Classifier
Authors	Brett Mullins
Abstract	We introduce the notion of pointwise coverage to measure the explainability properties of machine learning classifiers. An explanation for a prediction is a definably simple region of the feature space sharing the same label as the prediction, and the coverage of an explanation measures its size or generalizability. With this notion of explanation, we investigate whether or not there is a natural characterization of the most explainable classifier. According with our intuitions, we prove that the binary linear classifier is uniquely the most explainable classifier up to negligible sets.
Tasks
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08595v2
PDF	https://arxiv.org/pdf/1910.08595v2.pdf
PWC	https://paperswithcode.com/paper/identifying-the-most-explainable-classifier
Repo
Framework

Four Things Everyone Should Know to Improve Batch Normalization


Title	Four Things Everyone Should Know to Improve Batch Normalization
Authors	Cecilia Summers, Michael J. Dinneen
Abstract	A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep architectures, it has been challenging both to generically improve upon Batch Normalization and to understand the circumstances that lend themselves to other enhancements. In this paper, we identify four improvements to the generic form of Batch Normalization and the circumstances under which they work, yielding performance gains across all batch sizes while requiring no additional computation during training. These contributions include proposing a method for reasoning about the current example in inference normalization statistics, fixing a training vs. inference discrepancy; recognizing and validating the powerful regularization effect of Ghost Batch Normalization for small and medium batch sizes; examining the effect of weight decay regularization on the scaling and shifting parameters gamma and beta; and identifying a new normalization algorithm for very small batch sizes by combining the strengths of Batch and Group Normalization. We validate our results empirically on six datasets: CIFAR-100, SVHN, Caltech-256, Oxford Flowers-102, CUB-2011, and ImageNet.
Tasks
Published	2019-06-09
URL	https://arxiv.org/abs/1906.03548v2
PDF	https://arxiv.org/pdf/1906.03548v2.pdf
PWC	https://paperswithcode.com/paper/four-things-everyone-should-know-to-improve
Repo
Framework

Context-Aware Embeddings for Automatic Art Analysis


Title	Context-Aware Embeddings for Automatic Art Analysis
Authors	Noa Garcia, Benjamin Renoust, Yuta Nakashima
Abstract	Automatic art analysis aims to classify and retrieve artistic representations from a collection of images by using computer vision and machine learning techniques. In this work, we propose to enhance visual representations from neural networks with contextual artistic information. Whereas visual representations are able to capture information about the content and the style of an artwork, our proposed context-aware embeddings additionally encode relationships between different artistic attributes, such as author, school, or historical period. We design two different approaches for using context in automatic art analysis. In the first one, contextual data is obtained through a multi-task learning model, in which several attributes are trained together to find visual relationships between elements. In the second approach, context is obtained through an art-specific knowledge graph, which encodes relationships between artistic attributes. An exhaustive evaluation of both of our models in several art analysis problems, such as author identification, type classification, or cross-modal retrieval, show that performance is improved by up to 7.3% in art classification and 37.24% in retrieval when context-aware embeddings are used.
Tasks	Art Analysis, Cross-Modal Retrieval, Multi-Task Learning
Published	2019-04-10
URL	http://arxiv.org/abs/1904.04985v1
PDF	http://arxiv.org/pdf/1904.04985v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-embeddings-for-automatic-art
Repo
Framework

Some Limit Properties of Markov Chains Induced by Stochastic Recursive Algorithms


Title	Some Limit Properties of Markov Chains Induced by Stochastic Recursive Algorithms
Authors	Abhishek Gupta, Gaurav Tendolkar, Hao Chen, Jianzong Pi
Abstract	Recursive stochastic algorithms have gained significant attention in the recent past due to data driven applications. Examples include stochastic gradient descent for solving large-scale optimization problems and empirical dynamic programming algorithms for solving Markov decision problems. These recursive stochastic algorithms approximates certain contraction operators and can be viewed within the framework of iterated random maps. Accordingly, we consider iterated random maps over a Polish space that simulates a contraction operator over that Polish space. Assume that the iterated maps are indexed by $n$ such that as $n\rightarrow\infty$, each realization of the random map converges (in some sense) to the contraction map it is simulating. We show that starting from the same initial condition, the distribution of the random sequence generated by the iterated random maps converge weakly to the trajectory generated by the contraction operator. We further show that under certain conditions, the time average of the random sequence converge to the spatial mean of the invariant distribution. We then apply these results to logistic regression, empirical value iteration, empirical Q value iteration, and empirical relative value iteration for finite state finite action MDPs.
Tasks
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10778v1
PDF	http://arxiv.org/pdf/1904.10778v1.pdf
PWC	https://paperswithcode.com/paper/some-limit-properties-of-markov-chains
Repo
Framework

Attention-Wrapped Hierarchical BLSTMs for DDI Extraction


Title	Attention-Wrapped Hierarchical BLSTMs for DDI Extraction
Authors	Vahab Mostafapour, Oğuz Dikenelli
Abstract	Drug-Drug Interactions (DDIs) Extraction refers to the efforts to generate hand-made or automatic tools to extract embedded information from text and literature in the biomedical domain. Because of restrictions in hand-made efforts and their lower speed, Machine-Learning, or Deep-Learning approaches have become more popular for extracting DDIs. In this study, we propose a novel and generic Deep-Learning model which wraps Hierarchical Bidirectional LSTMs with two Attention Mechanisms that outperforms state-of-the-art models for DDIs Extraction, based on the DDIExtraction-2013 corpora. This model has obtained the macro F1-score of 0.785, and the precision of 0.80.
Tasks
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13561v1
PDF	https://arxiv.org/pdf/1907.13561v1.pdf
PWC	https://paperswithcode.com/paper/attention-wrapped-hierarchical-blstms-for-ddi
Repo
Framework

Learning Deep Generative Models with Short Run Inference Dynamics


Title	Learning Deep Generative Models with Short Run Inference Dynamics
Authors	Erik Nijkamp, Bo Pang, Tian Han, Linqi Zhou, Song-Chun Zhu, Ying Nian Wu
Abstract	This paper studies the fundamental problem of learning deep generative models that consist of one or more layers of latent variables organized in top-down architectures. Learning such a generative model requires inferring the latent variables for each training example based on the posterior distribution of these latent variables. The inference typically requires Markov chain Monte Caro (MCMC) that can be time consuming. In this paper, we propose to use short run inference dynamics guided by the log-posterior, such as finite-step gradient descent algorithm initialized from the prior distribution of the latent variables, as an approximate sampler of the posterior distribution, where the step size of the gradient descent dynamics is optimized by minimizing the Kullback-Leibler divergence between the distribution produced by the short run inference dynamics and the posterior distribution. Our experiments show that the proposed method outperforms variational auto-encoder (VAE) in terms of reconstruction error and synthesis quality. The advantage of the proposed method is that it is natural and automatic, even for models with multiple layers of latent variables.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01909v3
PDF	https://arxiv.org/pdf/1912.01909v3.pdf
PWC	https://paperswithcode.com/paper/learning-deep-generative-models-with-short
Repo
Framework

Preservation of Anomalous Subgroups On Machine Learning Transformed Data


Title	Preservation of Anomalous Subgroups On Machine Learning Transformed Data
Authors	Samuel C. Maina, Reginald E. Bryant, William O. Goal, Robert-Florian Samoilescu, Kush R. Varshney, Komminist Weldemariam
Abstract	In this paper, we investigate the effect of machine learning based anonymization on anomalous subgroup preservation. In particular, we train a binary classifier to discover the most anomalous subgroup in a dataset by maximizing the bias between the group’s predicted odds ratio from the model and observed odds ratio from the data. We then perform anonymization using a variational autoencoder (VAE) to synthesize an entirely new dataset that would ideally be drawn from the distribution of the original data. We repeat the anomalous subgroup discovery task on the new data and compare it to what was identified pre-anonymization. We evaluated our approach using publicly available datasets from the financial industry. Our evaluation confirmed that the approach was able to produce synthetic datasets that preserved a high level of subgroup differentiation as identified initially in the original dataset. Such a distinction was maintained while having distinctly different records between the synthetic and original dataset. Finally, we packed the above end to end process into what we call Utility Guaranteed Deep Privacy (UGDP) system. UGDP can be easily extended to onboard alternative generative approaches such as GANs to synthesize tabular data.
Tasks
Published	2019-11-09
URL	https://arxiv.org/abs/1911.03674v1
PDF	https://arxiv.org/pdf/1911.03674v1.pdf
PWC	https://paperswithcode.com/paper/preservation-of-anomalous-subgroups-on
Repo
Framework