July 27, 2019

3240 words 16 mins read

Paper Group ANR 702

An In-field Automatic Wheat Disease Diagnosis System. Neural Machine Translation by Generating Multiple Linguistic Factors. Color Orchestra: Ordering Color Palettes for Interpolation and Prediction. Restoration of Atmospheric Turbulence-distorted Images via RPCA and Quasiconformal Maps. Shared Learning : Enhancing Reinforcement in $Q$-Ensembles. Pr …

An In-field Automatic Wheat Disease Diagnosis System


Title	An In-field Automatic Wheat Disease Diagnosis System
Authors	Jiang Lu, Jie Hu, Guannan Zhao, Fenghua Mei, Changshui Zhang
Abstract	Crop diseases are responsible for the major production reduction and economic losses in agricultural industry world- wide. Monitoring for health status of crops is critical to control the spread of diseases and implement effective management. This paper presents an in-field automatic wheat disease diagnosis system based on a weakly super- vised deep learning framework, i.e. deep multiple instance learning, which achieves an integration of identification for wheat diseases and localization for disease areas with only image-level annotation for training images in wild conditions. Furthermore, a new in-field image dataset for wheat disease, Wheat Disease Database 2017 (WDD2017), is collected to verify the effectiveness of our system. Under two different architectures, i.e. VGG-FCN-VD16 and VGG-FCN-S, our system achieves the mean recognition accuracies of 97.95% and 95.12% respectively over 5-fold cross-validation on WDD2017, exceeding the results of 93.27% and 73.00% by two conventional CNN frameworks, i.e. VGG-CNN-VD16 and VGG-CNN-S. Experimental results demonstrate that the proposed system outperforms conventional CNN architectures on recognition accuracy under the same amount of parameters, meanwhile main- taining accurate localization for corresponding disease areas. Moreover, the proposed system has been packed into a real-time mobile app to provide support for agricultural disease diagnosis.
Tasks	Multiple Instance Learning
Published	2017-09-26
URL	http://arxiv.org/abs/1710.08299v1
PDF	http://arxiv.org/pdf/1710.08299v1.pdf
PWC	https://paperswithcode.com/paper/an-in-field-automatic-wheat-disease-diagnosis
Repo
Framework

Neural Machine Translation by Generating Multiple Linguistic Factors


Title	Neural Machine Translation by Generating Multiple Linguistic Factors
Authors	Mercedes García-Martínez, Loïc Barrault, Fethi Bougares
Abstract	Factored neural machine translation (FNMT) is founded on the idea of using the morphological and grammatical decomposition of the words (factors) at the output side of the neural network. This architecture addresses two well-known problems occurring in MT, namely the size of target language vocabulary and the number of unknown tokens produced in the translation. FNMT system is designed to manage larger vocabulary and reduce the training time (for systems with equivalent target language vocabulary size). Moreover, we can produce grammatically correct words that are not part of the vocabulary. FNMT model is evaluated on IWSLT’15 English to French task and compared to the baseline word-based and BPE-based NMT systems. Promising qualitative and quantitative results (in terms of BLEU and METEOR) are reported.
Tasks	Machine Translation
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01821v1
PDF	http://arxiv.org/pdf/1712.01821v1.pdf
PWC	https://paperswithcode.com/paper/neural-machine-translation-by-generating
Repo
Framework

Color Orchestra: Ordering Color Palettes for Interpolation and Prediction


Title	Color Orchestra: Ordering Color Palettes for Interpolation and Prediction
Authors	Huy Q. Phan, Hongbo Fu, Antoni B. Chan
Abstract	Color theme or color palette can deeply influence the quality and the feeling of a photograph or a graphical design. Although color palettes may come from different sources such as online crowd-sourcing, photographs and graphical designs, in this paper, we consider color palettes extracted from fine art collections, which we believe to be an abundant source of stylistic and unique color themes. We aim to capture color styles embedded in these collections by means of statistical models and to build practical applications upon these models. As artists often use their personal color themes in their paintings, making these palettes appear frequently in the dataset, we employed density estimation to capture the characteristics of palette data. Via density estimation, we carried out various predictions and interpolations on palettes, which led to promising applications such as photo-style exploration, real-time color suggestion, and enriched photo recolorization. It was, however, challenging to apply density estimation to palette data as palettes often come as unordered sets of colors, which make it difficult to use conventional metrics on them. To this end, we developed a divide-and-conquer sorting algorithm to rearrange the colors in the palettes in a coherent order, which allows meaningful interpolation between color palettes. To confirm the performance of our model, we also conducted quantitative experiments on datasets of digitized paintings collected from the Internet and received favorable results.
Tasks	Density Estimation
Published	2017-03-17
URL	http://arxiv.org/abs/1703.06003v1
PDF	http://arxiv.org/pdf/1703.06003v1.pdf
PWC	https://paperswithcode.com/paper/color-orchestra-ordering-color-palettes-for
Repo
Framework

Restoration of Atmospheric Turbulence-distorted Images via RPCA and Quasiconformal Maps


Title	Restoration of Atmospheric Turbulence-distorted Images via RPCA and Quasiconformal Maps
Authors	Chun Pong Lau, Yu Hin Lai, Lok Ming Lui
Abstract	We address the problem of restoring a high-quality image from an observed image sequence strongly distorted by atmospheric turbulence. A novel algorithm is proposed in this paper to reduce geometric distortion as well as space-and-time-varying blur due to strong turbulence. By considering a suitable energy functional, our algorithm first obtains a sharp reference image and a subsampled image sequence containing sharp and mildly distorted image frames with respect to the reference image. The subsampled image sequence is then stabilized by applying the Robust Principal Component Analysis (RPCA) on the deformation fields between image frames and warping the image frames by a quasiconformal map associated with the low-rank part of the deformation matrix. After image frames are registered to the reference image, the low-rank part of them are deblurred via a blind deconvolution, and the deblurred frames are then fused with the enhanced sparse part. Experiments have been carried out on both synthetic and real turbulence-distorted video. Results demonstrate that our method is effective in alleviating distortions and blur, restoring image details and enhancing visual quality.
Tasks
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03140v2
PDF	http://arxiv.org/pdf/1704.03140v2.pdf
PWC	https://paperswithcode.com/paper/restoration-of-atmospheric-turbulence
Repo
Framework

Shared Learning : Enhancing Reinforcement in $Q$-Ensembles


Title	Shared Learning : Enhancing Reinforcement in $Q$-Ensembles
Authors	Rakesh R Menon, Balaraman Ravindran
Abstract	Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward. However, most of these successes rely on algorithms that require a large amount of data to train in order to obtain results on par with human-level performance. This is not feasible if we are to deploy these systems on real world tasks and hence there has been an increased thrust in exploring data efficient algorithms. To this end, we propose the Shared Learning framework aimed at making $Q$-ensemble algorithms data-efficient. For achieving this, we look into some principles of transfer learning which aim to study the benefits of information exchange across tasks in reinforcement learning and adapt transfer to learning our value function estimates in a novel manner. In this paper, we consider the special case of transfer between the value function estimates in the $Q$-ensemble architecture of BootstrappedDQN. We further empirically demonstrate how our proposed framework can help in speeding up the learning process in $Q$-ensembles with minimum computational overhead on a suite of Atari 2600 Games.
Tasks	Atari Games, Continuous Control, Transfer Learning
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04909v1
PDF	http://arxiv.org/pdf/1709.04909v1.pdf
PWC	https://paperswithcode.com/paper/shared-learning-enhancing-reinforcement-in-q
Repo
Framework

Practical Bayesian optimization in the presence of outliers


Title	Practical Bayesian optimization in the presence of outliers
Authors	Ruben Martinez-Cantin, Kevin Tee, Michael McCourt
Abstract	Inference in the presence of outliers is an important field of research as outliers are ubiquitous and may arise across a variety of problems and domains. Bayesian optimization is method that heavily relies on probabilistic inference. This allows outstanding sample efficiency because the probabilistic machinery provides a memory of the whole optimization process. However, that virtue becomes a disadvantage when the memory is populated with outliers, inducing bias in the estimation. In this paper, we present an empirical evaluation of Bayesian optimization methods in the presence of outliers. The empirical evidence shows that Bayesian optimization with robust regression often produces suboptimal results. We then propose a new algorithm which combines robust regression (a Gaussian process with Student-t likelihood) with outlier diagnostics to classify data points as outliers or inliers. By using an scheduler for the classification of outliers, our method is more efficient and has better convergence over the standard robust regression. Furthermore, we show that even in controlled situations with no expected outliers, our method is able to produce better results.
Tasks
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04567v1
PDF	http://arxiv.org/pdf/1712.04567v1.pdf
PWC	https://paperswithcode.com/paper/practical-bayesian-optimization-in-the
Repo
Framework

Semantic Texture for Robust Dense Tracking


Title	Semantic Texture for Robust Dense Tracking
Authors	Jan Czarnowski, Stefan Leutenegger, Andrew Davison
Abstract	We argue that robust dense SLAM systems can make valuable use of the layers of features coming from a standard CNN as a pyramid of `semantic texture’ which is suitable for dense alignment while being much more robust to nuisance factors such as lighting than raw RGB values. We use a straightforward Lucas-Kanade formulation of image alignment, with a schedule of iterations over the coarse-to-fine levels of a pyramid, and simply replace the usual image pyramid by the hierarchy of convolutional feature maps from a pre-trained CNN. The resulting dense alignment performance is much more robust to lighting and other variations, as we show by camera rotation tracking experiments on time-lapse sequences captured over many hours. Looking towards the future of scene representation for real-time visual SLAM, we further demonstrate that a selection using simple criteria of a small number of the total set of features output by a CNN gives just as accurate but much more efficient tracking performance. \|
Tasks
Published	2017-08-29
URL	http://arxiv.org/abs/1708.08844v1
PDF	http://arxiv.org/pdf/1708.08844v1.pdf
PWC	https://paperswithcode.com/paper/semantic-texture-for-robust-dense-tracking
Repo
Framework

Dictionary Learning from Incomplete Data


Title	Dictionary Learning from Incomplete Data
Authors	Valeriya Naumova, Karin Schnass
Abstract	This paper extends the recently proposed and theoretically justified iterative thresholding and $K$ residual means algorithm ITKrM to learning dicionaries from incomplete/masked training data (ITKrMM). It further adapts the algorithm to the presence of a low rank component in the data and provides a strategy for recovering this low rank component again from incomplete data. Several synthetic experiments show the advantages of incorporating information about the corruption into the algorithm. Finally, image inpainting is considered as application example, which demonstrates the superior performance of ITKrMM in terms of speed at similar or better reconstruction quality compared to its closest dictionary learning counterpart.
Tasks	Dictionary Learning, Image Inpainting
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03655v2
PDF	http://arxiv.org/pdf/1701.03655v2.pdf
PWC	https://paperswithcode.com/paper/dictionary-learning-from-incomplete-data
Repo
Framework

Shallow Updates for Deep Reinforcement Learning


Title	Shallow Updates for Deep Reinforcement Learning
Authors	Nir Levine, Tom Zahavy, Daniel J. Mankowitz, Aviv Tamar, Shie Mannor
Abstract	Deep reinforcement learning (DRL) methods such as the Deep Q-Network (DQN) have achieved state-of-the-art results in a variety of challenging, high-dimensional domains. This success is mainly attributed to the power of deep neural networks to learn rich domain representations for approximating the value function or policy. Batch reinforcement learning methods with linear representations, on the other hand, are more stable and require less hyper parameter tuning. Yet, substantial feature engineering is necessary to achieve good results. In this work we propose a hybrid approach – the Least Squares Deep Q-Network (LS-DQN), which combines rich feature representations learned by a DRL algorithm with the stability of a linear least squares method. We do this by periodically re-training the last hidden layer of a DRL network with a batch least squares update. Key to our approach is a Bayesian regularization term for the least squares update, which prevents over-fitting to the more recent data. We tested LS-DQN on five Atari games and demonstrate significant improvement over vanilla DQN and Double-DQN. We also investigated the reasons for the superior performance of our method. Interestingly, we found that the performance improvement can be attributed to the large batch size used by the LS method when optimizing the last layer.
Tasks	Atari Games, Feature Engineering
Published	2017-05-21
URL	http://arxiv.org/abs/1705.07461v2
PDF	http://arxiv.org/pdf/1705.07461v2.pdf
PWC	https://paperswithcode.com/paper/shallow-updates-for-deep-reinforcement
Repo
Framework

Deep learning for plasma tomography using the bolometer system at JET


Title	Deep learning for plasma tomography using the bolometer system at JET
Authors	Francisco A. Matos, Diogo R. Ferreira, Pedro J. Carvalho, JET Contributors
Abstract	Deep learning is having a profound impact in many fields, especially those that involve some form of image processing. Deep neural networks excel in turning an input image into a set of high-level features. On the other hand, tomography deals with the inverse problem of recreating an image from a number of projections. In plasma diagnostics, tomography aims at reconstructing the cross-section of the plasma from radiation measurements. This reconstruction can be computed with neural networks. However, previous attempts have focused on learning a parametric model of the plasma profile. In this work, we use a deep neural network to produce a full, pixel-by-pixel reconstruction of the plasma profile. For this purpose, we use the overview bolometer system at JET, and we introduce an up-convolutional network that has been trained and tested on a large set of sample tomograms. We show that this network is able to reproduce existing reconstructions with a high level of accuracy, as measured by several metrics.
Tasks
Published	2017-01-02
URL	http://arxiv.org/abs/1701.00322v1
PDF	http://arxiv.org/pdf/1701.00322v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-plasma-tomography-using-the
Repo
Framework

DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations


Title	DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations
Authors	Ke Yan, Xiaosong Wang, Le Lu, Ronald M. Summers
Abstract	Extracting, harvesting and building large-scale annotated radiological image datasets is a greatly important yet challenging problem. It is also the bottleneck to designing more effective data-hungry computing paradigms (e.g., deep learning) for medical image analysis. Yet, vast amounts of clinical annotations (usually associated with disease image findings and marked using arrows, lines, lesion diameters, segmentation, etc.) have been collected over several decades and stored in hospitals’ Picture Archiving and Communication Systems. In this paper, we mine and harvest one major type of clinical annotation data - lesion diameters annotated on bookmarked images - to learn an effective multi-class lesion detector via unsupervised and supervised deep Convolutional Neural Networks (CNN). Our dataset is composed of 33,688 bookmarked radiology images from 10,825 studies of 4,477 unique patients. For every bookmarked image, a bounding box is created to cover the target lesion based on its measured diameters. We categorize the collection of lesions using an unsupervised deep mining scheme to generate clustered pseudo lesion labels. Next, we adopt a regional-CNN method to detect lesions of multiple categories, regardless of missing annotations (normally only one lesion is annotated, despite the presence of multiple co-existing findings). Our integrated mining, categorization and detection framework is validated with promising empirical results, as a scalable, universal or multi-purpose CAD paradigm built upon abundant retrospective medical data. Furthermore, we demonstrate that detection accuracy can be significantly improved by incorporating pseudo lesion labels (e.g., Liver lesion/tumor, Lung nodule/tumor, Abdomen lesions, Chest lymph node and others). This dataset will be made publicly available (under the open science initiative).
Tasks	Lesion Segmentation
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01766v2
PDF	http://arxiv.org/pdf/1710.01766v2.pdf
PWC	https://paperswithcode.com/paper/deeplesion-automated-deep-mining
Repo
Framework

A Unified Framework for Stochastic Matrix Factorization via Variance Reduction


Title	A Unified Framework for Stochastic Matrix Factorization via Variance Reduction
Authors	Renbo Zhao, William B. Haskell, Jiashi Feng
Abstract	We propose a unified framework to speed up the existing stochastic matrix factorization (SMF) algorithms via variance reduction. Our framework is general and it subsumes several well-known SMF formulations in the literature. We perform a non-asymptotic convergence analysis of our framework and derive computational and sample complexities for our algorithm to converge to an $\epsilon$-stationary point in expectation. In addition, extensive experiments for a wide class of SMF formulations demonstrate that our framework consistently yields faster convergence and a more accurate output dictionary vis-`a-vis state-of-the-art frameworks.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.06884v2
PDF	http://arxiv.org/pdf/1705.06884v2.pdf
PWC	https://paperswithcode.com/paper/a-unified-framework-for-stochastic-matrix
Repo
Framework

A Unified Method for First and Third Person Action Recognition


Title	A Unified Method for First and Third Person Action Recognition
Authors	Ali Javidani, Ahmad Mahmoudi-Aznaveh
Abstract	In this paper, a new video classification methodology is proposed which can be applied in both first and third person videos. The main idea behind the proposed strategy is to capture complementary information of appearance and motion efficiently by performing two independent streams on the videos. The first stream is aimed to capture long-term motions from shorter ones by keeping track of how elements in optical flow images have changed over time. Optical flow images are described by pre-trained networks that have been trained on large scale image datasets. A set of multi-channel time series are obtained by aligning descriptions beside each other. For extracting motion features from these time series, PoT representation method plus a novel pooling operator is followed due to several advantages. The second stream is accomplished to extract appearance features which are vital in the case of video classification. The proposed method has been evaluated on both first and third-person datasets and results present that the proposed methodology reaches the state of the art successfully.
Tasks	Optical Flow Estimation, Temporal Action Localization, Time Series, Video Classification
Published	2017-12-30
URL	http://arxiv.org/abs/1801.00192v2
PDF	http://arxiv.org/pdf/1801.00192v2.pdf
PWC	https://paperswithcode.com/paper/a-unified-method-for-first-and-third-person
Repo
Framework

3D Surface-to-Structure Translation using Deep Convolutional Networks


Title	3D Surface-to-Structure Translation using Deep Convolutional Networks
Authors	Takumi Moriya, Kazuyuki Saito, Hiroya Tanaka
Abstract	Our demonstration shows a system that estimates internal body structures from 3D surface models using deep convolutional neural networks trained on CT (computed tomography) images of the human body. To take pictures of structures inside the body, we need to use a CT scanner or an MRI (Magnetic Resonance Imaging) scanner. However, assuming that the mutual information between outer shape of the body and its inner structure is not zero, we can obtain an approximate internal structure from a 3D surface model based on MRI and CT image database. This suggests that we could know where and what kind of disease a person is likely to have in his/her body simply by 3D scanning surface of the body. As a first prototype, we developed a system for estimating internal body structures from surface models based on Visible Human Project DICOM CT Datasets from the University of Iowa Magnetic Resonance Research Facility.
Tasks
Published	2017-12-08
URL	http://arxiv.org/abs/1801.01449v1
PDF	http://arxiv.org/pdf/1801.01449v1.pdf
PWC	https://paperswithcode.com/paper/3d-surface-to-structure-translation-using
Repo
Framework


Title	Semantically Informed Multiview Surface Refinement
Authors	Maros Blaha, Mathias Rothermel, Martin R. Oswald, Torsten Sattler, Audrey Richard, Jan D. Wegner, Marc Pollefeys, Konrad Schindler
Abstract	We present a method to jointly refine the geometry and semantic segmentation of 3D surface meshes. Our method alternates between updating the shape and the semantic labels. In the geometry refinement step, the mesh is deformed with variational energy minimization, such that it simultaneously maximizes photo-consistency and the compatibility of the semantic segmentations across a set of calibrated images. Label-specific shape priors account for interactions between the geometry and the semantic labels in 3D. In the semantic segmentation step, the labels on the mesh are updated with MRF inference, such that they are compatible with the semantic segmentations in the input images. Also, this step includes prior assumptions about the surface shape of different semantic classes. The priors induce a tight coupling, where semantic information influences the shape update and vice versa. Specifically, we introduce priors that favor (i) adaptive smoothing, depending on the class label; (ii) straightness of class boundaries; and (iii) semantic labels that are consistent with the surface orientation. The novel mesh-based reconstruction is evaluated in a series of experiments with real and synthetic data. We compare both to state-of-the-art, voxel-based semantic 3D reconstruction, and to purely geometric mesh refinement, and demonstrate that the proposed scheme yields improved 3D geometry as well as an improved semantic segmentation.
Tasks	3D Reconstruction, Semantic Segmentation
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08336v1
PDF	http://arxiv.org/pdf/1706.08336v1.pdf
PWC	https://paperswithcode.com/paper/semantically-informed-multiview-surface
Repo
Framework