January 25, 2020

3382 words 16 mins read

Paper Group ANR 1779

AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results. Frequency Separation for Real-World Super-Resolution. Training Set Effect on Super Resolution for Automated Target Recognition. Text Summarization in the Biomedical Domain. Summary Refinement through Denoising. STRASS: A Light and Effective Method for Extractive Summariza …

AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results


Title	AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results
Authors	Andreas Lugmayr, Martin Danelljan, Radu Timofte, Manuel Fritsche, Shuhang Gu, Kuldeep Purohit, Praveen Kandula, Maitreya Suin, A N Rajagopalan, Nam Hyung Joon, Yu Seung Won, Guisik Kim, Dokyeong Kwon, Chih-Chung Hsu, Chia-Hsiang Lin, Yuanfei Huang, Xiaopeng Sun, Wen Lu, Jie Li, Xinbo Gao, Sefi Bell-Kligler
Abstract	This paper reviews the AIM 2019 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided in the challenge. In Track 1: Source Domain the aim is to super-resolve such images while preserving the low level image characteristics of the source input domain. In Track 2: Target Domain a set of high-quality images is also provided for training, that defines the output domain and desired quality of the super-resolved images. To allow for quantitative evaluation, the source input images in both tracks are constructed using artificial, but realistic, image degradations. The challenge is the first of its kind, aiming to advance the state-of-the-art and provide a standard benchmark for this newly emerging task. In total 7 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07783v2
PDF	https://arxiv.org/pdf/1911.07783v2.pdf
PWC	https://paperswithcode.com/paper/aim-2019-challenge-on-real-world-image-super
Repo
Framework

Frequency Separation for Real-World Super-Resolution


Title	Frequency Separation for Real-World Super-Resolution
Authors	Manuel Fritsche, Shuhang Gu, Radu Timofte
Abstract	Most of the recent literature on image super-resolution (SR) assumes the availability of training data in the form of paired low resolution (LR) and high resolution (HR) images or the knowledge of the downgrading operator (usually bicubic downscaling). While the proposed methods perform well on standard benchmarks, they often fail to produce convincing results in real-world settings. This is because real-world images can be subject to corruptions such as sensor noise, which are severely altered by bicubic downscaling. Therefore, the models never see a real-world image during training, which limits their generalization capabilities. Moreover, it is cumbersome to collect paired LR and HR images in the same source domain. To address this problem, we propose DSGAN to introduce natural image characteristics in bicubically downscaled images. It can be trained in an unsupervised fashion on HR images, thereby generating LR images with the same characteristics as the original images. We then use the generated data to train a SR model, which greatly improves its performance on real-world images. Furthermore, we propose to separate the low and high image frequencies and treat them differently during training. Since the low frequencies are preserved by downsampling operations, we only require adversarial training to modify the high frequencies. This idea is applied to our DSGAN model as well as the SR model. We demonstrate the effectiveness of our method in several experiments through quantitative and qualitative analysis. Our solution is the winner of the AIM Challenge on Real World SR at ICCV 2019.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07850v1
PDF	https://arxiv.org/pdf/1911.07850v1.pdf
PWC	https://paperswithcode.com/paper/frequency-separation-for-real-world-super
Repo
Framework

Training Set Effect on Super Resolution for Automated Target Recognition


Title	Training Set Effect on Super Resolution for Automated Target Recognition
Authors	Matthew Ciolino, David Noever, Josh Kalin
Abstract	Single Image Super Resolution (SISR) is the process of mapping a low-resolution image to a high resolution image. This inherently has applications in remote sensing as a way to increase the spatial resolution in satellite imagery. This suggests a possible improvement to automated target recognition in image classification and object detection. We explore the effect that different training sets have on SISR with the network, Super Resolution Generative Adversarial Network (SRGAN). We train 5 SRGANs on different land-use classes (e.g. agriculture, cities, ports) and test them on the same unseen dataset. We attempt to find the qualitative and quantitative differences in SISR, binary classification, and object detection performance. We find that curated training sets that contain objects in the test ontology perform better on both computer vision tasks while having a complex distribution of images allows object detection models to perform better. However, Super Resolution (SR) might not be beneficial to certain problems and will see a diminishing amount of returns for datasets that are closer to being solved.
Tasks	Image Classification, Image Super-Resolution, Object Detection, Super-Resolution
Published	2019-10-29
URL	https://arxiv.org/abs/1911.07934v3
PDF	https://arxiv.org/pdf/1911.07934v3.pdf
PWC	https://paperswithcode.com/paper/training-set-affect-on-super-resolution-for
Repo
Framework

Text Summarization in the Biomedical Domain


Title	Text Summarization in the Biomedical Domain
Authors	Milad Moradi, Nasser Ghadiri
Abstract	This chapter gives an overview of recent advances in the field of biomedical text summarization. Different types of challenges are introduced, and methods are discussed concerning the type of challenge that they address. Biomedical literature summarization is explored as a leading trend in the field, and some future lines of work are pointed out. Underlying methods of recent summarization systems are briefly explained and the most significant evaluation results are mentioned. The primary purpose of this chapter is to review the most significant research efforts made in the current decade toward new methods of biomedical text summarization. As the main parts of this chapter, current trends are discussed and new challenges are introduced.
Tasks	Text Summarization
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02285v1
PDF	https://arxiv.org/pdf/1908.02285v1.pdf
PWC	https://paperswithcode.com/paper/text-summarization-in-the-biomedical-domain
Repo
Framework

Summary Refinement through Denoising


Title	Summary Refinement through Denoising
Authors	Nikola I. Nikolov, Alessandro Calmanovici, Richard H. R. Hahnloser
Abstract	We propose a simple method for post-processing the outputs of a text summarization system in order to refine its overall quality. Our approach is to train text-to-text rewriting models to correct information redundancy errors that may arise during summarization. We train on synthetically generated noisy summaries, testing three different types of noise that introduce out-of-context information within each summary. When applied on top of extractive and abstractive summarization baselines, our summary denoising models yield metric improvements while reducing redundancy.
Tasks	Abstractive Text Summarization, Denoising, Text Summarization
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10873v1
PDF	https://arxiv.org/pdf/1907.10873v1.pdf
PWC	https://paperswithcode.com/paper/summary-refinement-through-denoising
Repo
Framework

STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings


Title	STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings
Authors	Léo Bouscarrat, Antoine Bonnefoy, Thomas Peel, Cécile Pereira
Abstract	This paper introduces STRASS: Summarization by TRAnsformation Selection and Scoring. It is an extractive text summarization method which leverages the semantic information in existing sentence embedding spaces. Our method creates an extractive summary by selecting the sentences with the closest embeddings to the document embedding. The model learns a transformation of the document embedding to minimize the similarity between the extractive summary and the ground truth summary. As the transformation is only composed of a dense layer, the training can be done on CPU, therefore, inexpensive. Moreover, inference time is short and linear according to the number of sentences. As a second contribution, we introduce the French CASS dataset, composed of judgments from the French Court of cassation and their corresponding summaries. On this dataset, our results show that our method performs similarly to the state of the art extractive methods with effective training and inferring time.
Tasks	Document Embedding, Sentence Embedding, Sentence Embeddings, Text Summarization
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07323v1
PDF	https://arxiv.org/pdf/1907.07323v1.pdf
PWC	https://paperswithcode.com/paper/strass-a-light-and-effective-method-for
Repo
Framework

High Accurate Unhealthy Leaf Detection


Title	High Accurate Unhealthy Leaf Detection
Authors	S. Mohan Sai, G. Gopichand, C. Vikas Reddy, K. Mona Teja
Abstract	India is an agriculture-dependent country. As we all know that farming is the backbone of our country it is our responsibility to preserve the crops. However, we cannot stop the destruction of crops by natural calamities at least we have to try to protect our crops from diseases. To, detect a plant disease we need a fast automatic way. So, this paper presents a model to identify the particular disease of plant leaves at early stages so that we can prevent or take a remedy to stop spreading of the disease. This proposed model is made into five sessions. Image preprocessing includes the enhancement of the low light image done using inception modules in CNN. Low-resolution image enhancement is done using an Adversarial Neural Network. This also includes Conversion of RGB Image to YCrCb color space. Next, this paper presents a methodology for image segmentation which is an important aspect for identifying the disease symptoms. This segmentation is done using the genetic algorithm. Due to this process the segmentation of the leaf Image this helps in detection of the leaf mage automatically and classifying. Texture extraction is done using the statistical model called GLCM and finally, the classification of the diseases is done using the SVM using Different Kernels with the high accuracy.
Tasks	Image Enhancement, Semantic Segmentation
Published	2019-08-14
URL	https://arxiv.org/abs/1908.09003v1
PDF	https://arxiv.org/pdf/1908.09003v1.pdf
PWC	https://paperswithcode.com/paper/high-accurate-unhealthy-leaf-detection
Repo
Framework

Multi-Zone Unit for Recurrent Neural Networks


Title	Multi-Zone Unit for Recurrent Neural Networks
Authors	Fandong Meng, Jinchao Zhang, Yang Liu, Jie Zhou
Abstract	Recurrent neural networks (RNNs) have been widely used to deal with sequence learning problems. The input-dependent transition function, which folds new observations into hidden states to sequentially construct fixed-length representations of arbitrary-length sequences, plays a critical role in RNNs. Based on single space composition, transition functions in existing RNNs often have difficulty in capturing complicated long-range dependencies. In this paper, we introduce a new Multi-zone Unit (MZU) for RNNs. The key idea is to design a transition function that is capable of modeling multiple space composition. The MZU consists of three components: zone generation, zone composition, and zone aggregation. Experimental results on multiple datasets of the character-level language modeling task and the aspect-based sentiment analysis task demonstrate the superiority of the MZU.
Tasks	Aspect-Based Sentiment Analysis, Language Modelling, Sentiment Analysis
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07184v1
PDF	https://arxiv.org/pdf/1911.07184v1.pdf
PWC	https://paperswithcode.com/paper/multi-zone-unit-for-recurrent-neural-networks
Repo
Framework

Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning


Title	Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning
Authors	Anis Elgabli, Jihong Park, Amrit S. Bedi, Chaouki Ben Issaid, Mehdi Bennis, Vaneet Aggarwal
Abstract	In this article, we propose a communication-efficient decentralized machine learning (ML) algorithm, coined quantized group ADMM (Q-GADMM). To reduce the number of communication links, every worker in Q-GADMM communicates only with two neighbors, while updating its model via the group alternating direct method of multiplier (GADMM). Next, each worker quantizes its model updates before transmission, thereby decreasing the communication payload size. However, due to the lack of centralized entity in decentralized ML, the communication link sparsification and payload compression may incur error propagation, hindering model training convergence. To overcome this, we develop a novel stochastic quantization method to adaptively adjust model quantization levels and their probabilities, while proving the convergence of Q-GADMM for convex objective functions. Furthermore, to demonstrate the feasibility of Q-GADMM for non-convex objective functions, we propose quantized stochastic GADMM (Q-SGADMM) that incorporates deep neural network architectures and stochastic gradient decent (SGD). Simulation results corroborate that Q-GADMM yields 7x less total communication cost while achieving almost the same accuracy and convergence speed compared to GADMM without quantization for a linear regression task. Similarly, for an image classification task, Q-SGADMM achieves 4x less total communication cost with identical accuracy and convergence speed compared to its counterpart without quantization, i.e., stochastic GADMM (SGADMM).
Tasks	Image Classification, Quantization
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10453v3
PDF	https://arxiv.org/pdf/1910.10453v3.pdf
PWC	https://paperswithcode.com/paper/q-gadmm-quantized-group-admm-for
Repo
Framework

f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning


Title	f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
Authors	Yongqin Xian, Saurabh Sharma, Bernt Schiele, Zeynep Akata
Abstract	When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zero- and few-shot learning settings. We also demonstrate that our learned features are interpretable: we visualize them by inverting them back to the pixel space and we explain them by generating textual arguments of why they are associated with a certain label.
Tasks	Data Augmentation, Few-Shot Learning
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10132v1
PDF	http://arxiv.org/pdf/1903.10132v1.pdf
PWC	https://paperswithcode.com/paper/f-vaegan-d2-a-feature-generating-framework
Repo
Framework

The Sparse Reverse of Principal Component Analysis for Fast Low-Rank Matrix Completion


Title	The Sparse Reverse of Principal Component Analysis for Fast Low-Rank Matrix Completion
Authors	Abdallah Chehade, Zunya Shi
Abstract	Matrix completion constantly receives tremendous attention from many research fields. It is commonly applied for recommender systems such as movie ratings, computer vision such as image reconstruction or completion, multi-task learning such as collaboratively modeling time-series trends of multiple sensors, and many other applications. Matrix completion techniques are usually computationally exhaustive and/or fail to capture the heterogeneity in the data. For example, images usually contain a heterogeneous set of objects, and thus it is a challenging task to reconstruct images with high levels of missing data. In this paper, we propose the sparse reverse of principal component analysis for matrix completion. The proposed approach maintains smoothness across the matrix, produces accurate estimates of the missing data, converges iteratively, and it is computationally tractable with a controllable upper bound on the number of iterations until convergence. The accuracy of the proposed technique is validated on natural images, movie ratings, and multisensor data. It is also compared with common benchmark methods used for matrix completion.
Tasks	Image Reconstruction, Low-Rank Matrix Completion, Matrix Completion, Multi-Task Learning, Recommendation Systems, Time Series
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02155v1
PDF	https://arxiv.org/pdf/1910.02155v1.pdf
PWC	https://paperswithcode.com/paper/the-sparse-reverse-of-principal-component
Repo
Framework

Jointly Adversarial Network to Wavelength Compensation and Dehazing of Underwater Images


Title	Jointly Adversarial Network to Wavelength Compensation and Dehazing of Underwater Images
Authors	Xueyan Ding, Yafei Wang, Yang Yan, Zheng Liang, Zetian Mi, Xianping Fu
Abstract	Severe color casts, low contrast and blurriness of underwater images caused by light absorption and scattering result in a difficult task for exploring underwater environments. Different from most of previous underwater image enhancement methods that compute light attenuation along object-camera path through hazy image formation model, we propose a novel jointly wavelength compensation and dehazing network (JWCDN) that takes into account the wavelength attenuation along surface-object path and the scattering along object-camera path simultaneously. By embedding a simplified underwater formation model into generative adversarial network, we can jointly estimates the transmission map, wavelength attenuation and background light via different network modules, and uses the simplified underwater image formation model to recover degraded underwater images. Especially, a multi-scale densely connected encoder-decoder network is proposed to leverage features from multiple layers for estimating the transmission map. To further improve the recovered image, we use an edge preserving network module to enhance the detail of the recovered image. Moreover, to train the proposed network, we propose a novel underwater image synthesis method that generates underwater images with inherent optical properties of different water types. The synthesis method can simulate the color, contrast and blurriness appearance of real-world underwater environments simultaneously. Extensive experiments on synthetic and real-world underwater images demonstrate that the proposed method yields comparable or better results on both subjective and objective assessments, compared with several state-of-the-art methods.
Tasks	Image Enhancement, Image Generation
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05595v1
PDF	https://arxiv.org/pdf/1907.05595v1.pdf
PWC	https://paperswithcode.com/paper/jointly-adversarial-network-to-wavelength
Repo
Framework

Anisotropic Super Resolution in Prostate MRI using Super Resolution Generative Adversarial Networks


Title	Anisotropic Super Resolution in Prostate MRI using Super Resolution Generative Adversarial Networks
Authors	Rewa Sood, Mirabela Rusu
Abstract	Acquiring High Resolution (HR) Magnetic Resonance (MR) images requires the patient to remain still for long periods of time, which causes patient discomfort and increases the probability of motion induced image artifacts. A possible solution is to acquire low resolution (LR) images and to process them with the Super Resolution Generative Adversarial Network (SRGAN) to create a super-resolved version. This work applies SRGAN to MR images of the prostate and performs three experiments. The first experiment explores improving the in-plane MR image resolution by factors of 4 and 8, and shows that, while the PSNR and SSIM (Structural SIMilarity) metrics are lower than the isotropic bicubic interpolation baseline, the SRGAN is able to create images that have high edge fidelity. The second experiment explores anisotropic super-resolution via synthetic images, in that the input images to the network are anisotropically downsampled versions of HR images. This experiment demonstrates the ability of the modified SRGAN to perform anisotropic super-resolution, with quantitative image metrics that are comparable to those of the anisotropic bicubic interpolation baseline. Finally, the third experiment applies a modified version of the SRGAN to super-resolve anisotropic images obtained from the through-plane slices of the volumetric MR data. The output super-resolved images contain a significant amount of high frequency information that make them visually close to their HR counterparts. Overall, the promising results from each experiment show that super-resolution for MR images is a successful technique and that producing isotropic MR image volumes from anisotropic slices is an achievable goal.
Tasks	Super-Resolution
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09497v1
PDF	https://arxiv.org/pdf/1912.09497v1.pdf
PWC	https://paperswithcode.com/paper/anisotropic-super-resolution-in-prostate-mri
Repo
Framework

Ordinal Bucketing for Game Trees using Dynamic Quantile Approximation


Title	Ordinal Bucketing for Game Trees using Dynamic Quantile Approximation
Authors	Tobias Joppen, Tilman Strübig, Johannes Fürnkranz
Abstract	In this paper, we present a simple and cheap ordinal bucketing algorithm that approximately generates $q$-quantiles from an incremental data stream. The bucketing is done dynamically in the sense that the amount of buckets $q$ increases with the number of seen samples. We show how this can be used in Ordinal Monte Carlo Tree Search (OMCTS) to yield better bounds on time and space complexity, especially in the presence of noisy rewards. Besides complexity analysis and quality tests of quantiles, we evaluate our method using OMCTS in the General Video Game Framework (GVGAI). Our results demonstrate its dominance over vanilla Monte Carlo Tree Search in the presence of noise, where OMCTS without bucketing has a very bad time and space complexity.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13449v1
PDF	https://arxiv.org/pdf/1905.13449v1.pdf
PWC	https://paperswithcode.com/paper/ordinal-bucketing-for-game-trees-using
Repo
Framework

Targeted Estimation of Heterogeneous Treatment Effect in Observational Survival Analysis


Title	Targeted Estimation of Heterogeneous Treatment Effect in Observational Survival Analysis
Authors	Jie Zhu, Blanca Gallego
Abstract	The aim of clinical effectiveness research using repositories of electronic health records is to identify what health interventions ‘work best’ in real-world settings. Since there are several reasons why the net benefit of intervention may differ across patients, current comparative effectiveness literature focuses on investigating heterogeneous treatment effect and predicting whether an individual might benefit from an intervention. The majority of this literature has concentrated on the estimation of the effect of treatment on binary outcomes. However, many medical interventions are evaluated in terms of their effect on future events, which are subject to loss to follow-up. In this study, we describe a framework for the estimation of heterogeneous treatment effect in terms of differences in time-to-event (survival) probabilities. We divide the problem into three phases: (1) estimation of treatment effect conditioned on unique sets of the covariate vector; (2) identification of features important for heterogeneity using an ensemble of non-parametric variable importance methods; and (3) estimation of treatment effect on the reference classes defined by the previously selected features, using one-step Targeted Maximum Likelihood Estimation. We conducted a series of simulation studies and found that this method performs well when either sample size or event rate is high enough and the number of covariates contributing to the effect heterogeneity is moderate. An application of this method to a clinical case study was conducted by estimating the effect of oral anticoagulants on newly diagnosed non-valvular atrial fibrillation patients using data from the UK Clinical Practice Research Datalink.
Tasks	Survival Analysis
Published	2019-10-20
URL	https://arxiv.org/abs/1910.08877v2
PDF	https://arxiv.org/pdf/1910.08877v2.pdf
PWC	https://paperswithcode.com/paper/targeted-estimation-of-heterogeneous
Repo
Framework