October 20, 2019

3531 words 17 mins read

Paper Group ANR 36

Explaining Black Boxes on Sequential Data using Weighted Automata. Super-pixel cloud detection using Hierarchical Fusion CNN. A two-stage hybrid model by using artificial neural networks as feature construction algorithms. Single Day Outdoor Photometric Stereo. Deep learning based cloud detection for medium and high resolution remote sensing images …

Explaining Black Boxes on Sequential Data using Weighted Automata


Title	Explaining Black Boxes on Sequential Data using Weighted Automata
Authors	Stephane Ayache, Remi Eyraud, Noe Goudian
Abstract	Understanding how a learned black box works is of crucial interest for the future of Machine Learning. In this paper, we pioneer the question of the global interpretability of learned black box models that assign numerical values to symbolic sequential data. To tackle that task, we propose a spectral algorithm for the extraction of weighted automata (WA) from such black boxes. This algorithm does not require the access to a dataset or to the inner representation of the black box: the inferred model can be obtained solely by querying the black box, feeding it with inputs and analyzing its outputs. Experiments using Recurrent Neural Networks (RNN) trained on a wide collection of 48 synthetic datasets and 2 real datasets show that the obtained approximation is of great quality.
Tasks
Published	2018-10-12
URL	http://arxiv.org/abs/1810.05741v1
PDF	http://arxiv.org/pdf/1810.05741v1.pdf
PWC	https://paperswithcode.com/paper/explaining-black-boxes-on-sequential-data
Repo
Framework

Super-pixel cloud detection using Hierarchical Fusion CNN


Title	Super-pixel cloud detection using Hierarchical Fusion CNN
Authors	Han Liu, Dan Zeng, Qi Tian
Abstract	Cloud detection plays a very important role in the process of remote sensing images. This paper designs a super-pixel level cloud detection method based on convolutional neural network (CNN) and deep forest. Firstly, remote sensing images are segmented into super-pixels through the combination of SLIC and SEEDS. Structured forests is carried out to compute edge probability of each pixel, based on which super-pixels are segmented more precisely. Segmented super-pixels compose a super-pixel level remote sensing database. Though cloud detection is essentially a binary classification problem, our database is labeled into four categories: thick cloud, cirrus cloud, building and other culture, to improve the generalization ability of our proposed models. Secondly, super-pixel level database is used to train our cloud detection models based on CNN and deep forest. Considering super-pixel level remote sensing images contain less semantic information compared with general object classification database, we propose a Hierarchical Fusion CNN (HFCNN). It takes full advantage of low-level features like color and texture information and is more applicable to cloud detection task. In test phase, every super-pixel in remote sensing images is classified by our proposed models and then combined to recover final binary mask by our proposed distance metric, which is used to determine ambiguous super-pixels. Experimental results show that, compared with conventional methods, HFCNN can achieve better precision and recall.
Tasks	Cloud Detection, Object Classification
Published	2018-10-19
URL	http://arxiv.org/abs/1810.08352v1
PDF	http://arxiv.org/pdf/1810.08352v1.pdf
PWC	https://paperswithcode.com/paper/super-pixel-cloud-detection-using
Repo
Framework

A two-stage hybrid model by using artificial neural networks as feature construction algorithms


Title	A two-stage hybrid model by using artificial neural networks as feature construction algorithms
Authors	Yan Wang, Xuelei Sherry Ni, Brian Stone
Abstract	We propose a two-stage hybrid approach with neural networks as the new feature construction algorithms for bankcard response classifications. The hybrid model uses a very simple neural network structure as the new feature construction tool in the first stage, then the newly created features are used as the additional input variables in logistic regression in the second stage. The model is compared with the traditional one-stage model in credit customer response classification. It is observed that the proposed two-stage model outperforms the one-stage model in terms of accuracy, the area under ROC curve, and KS statistic. By creating new features with the neural network technique, the underlying nonlinear relationships between variables are identified. Furthermore, by using a very simple neural network structure, the model could overcome the drawbacks of neural networks in terms of its long training time, complex topology, and limited interpretability.
Tasks
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02546v1
PDF	http://arxiv.org/pdf/1812.02546v1.pdf
PWC	https://paperswithcode.com/paper/a-two-stage-hybrid-model-by-using-artificial
Repo
Framework

Single Day Outdoor Photometric Stereo


Title	Single Day Outdoor Photometric Stereo
Authors	Yannick Hold-Geoffroy, Paulo F. U. Gotardo, Jean-François Lalonde
Abstract	Photometric Stereo (PS) under outdoor illumination remains a challenging, ill-posed problem due to insufficient variability in illumination. Months-long capture sessions are typically used in this setup, with little success on shorter, single-day time intervals. In this paper, we investigate the solution of outdoor PS over a single day, under different weather conditions. First, we investigate the relationship between weather and surface reconstructability in order to understand when natural lighting allows existing PS algorithms to work. Our analysis reveals that partially cloudy days improve the conditioning of the outdoor PS problem while sunny days do not allow the unambiguous recovery of surface normals from photometric cues alone. We demonstrate that calibrated PS algorithms can thus be employed to reconstruct Lambertian surfaces accurately under partially cloudy days. Second, we solve the ambiguity arising in clear days by combining photometric cues with prior knowledge on material properties, local surface geometry and the natural variations in outdoor lighting through a CNN-based, weakly-calibrated PS technique. Given a sequence of outdoor images captured during a single sunny day, our method robustly estimates the scene surface normals with unprecedented quality for the considered scenario. Our approach does not require precise geolocation and significantly outperforms several state-of-the-art methods on images with real lighting, showing that our CNN can combine efficiently learned priors and photometric cues available during a single sunny day.
Tasks
Published	2018-03-28
URL	https://arxiv.org/abs/1803.10850v4
PDF	https://arxiv.org/pdf/1803.10850v4.pdf
PWC	https://paperswithcode.com/paper/deep-photometric-stereo-on-a-sunny-day
Repo
Framework

Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors


Title	Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors
Authors	Zhiwei Li, Huanfeng Shen, Qing Cheng, Yuhao Liu, Shucheng You, Zongyi He
Abstract	Cloud detection is an important preprocessing step for the precise application of optical satellite imagery. In this paper, we propose a deep learning based cloud detection method named multi-scale convolutional feature fusion (MSCFF) for remote sensing images of different sensors. In the network architecture of MSCFF, the symmetric encoder-decoder module, which provides both local and global context by densifying feature maps with trainable convolutional filter banks, is utilized to extract multi-scale and high-level spatial features. The feature maps of multiple scales are then up-sampled and concatenated, and a novel multi-scale feature fusion module is designed to fuse the features of different scales for the output. The two output feature maps of the network are cloud and cloud shadow maps, which are in turn fed to binary classifiers outside the model to obtain the final cloud and cloud shadow mask. The MSCFF method was validated on hundreds of globally distributed optical satellite images, with spatial resolutions ranging from 0.5 to 50 m, including Landsat-5/7/8, Gaofen-1/2/4, Sentinel-2, Ziyuan-3, CBERS-04, Huanjing-1, and collected high-resolution images exported from Google Earth. The experimental results show that MSCFF achieves a higher accuracy than the traditional rule-based cloud detection methods and the state-of-the-art deep learning models, especially in bright surface covered areas. The effectiveness of MSCFF means that it has great promise for the practical application of cloud detection for multiple types of medium and high-resolution remote sensing images. Our established global high-resolution cloud detection validation dataset has been made available online.
Tasks	Cloud Detection
Published	2018-10-13
URL	http://arxiv.org/abs/1810.05801v3
PDF	http://arxiv.org/pdf/1810.05801v3.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-cloud-detection-for
Repo
Framework

Online Deep Learning: Growing RBM on the fly


Title	Online Deep Learning: Growing RBM on the fly
Authors	Savitha Ramasamy, Kanagasabai Rajaraman, Pavitra Krishnaswamy, Vijay Chandrasekhar
Abstract	We propose a novel online learning algorithm for Restricted Boltzmann Machines (RBM), namely, the Online Generative Discriminative Restricted Boltzmann Machine (OGD-RBM), that provides the ability to build and adapt the network architecture of RBM according to the statistics of streaming data. The OGD-RBM is trained in two phases: (1) an online generative phase for unsupervised feature representation at the hidden layer and (2) a discriminative phase for classification. The online generative training begins with zero neurons in the hidden layer, adds and updates the neurons to adapt to statistics of streaming data in a single pass unsupervised manner, resulting in a feature representation best suited to the data. The discriminative phase is based on stochastic gradient descent and associates the represented features to the class labels. We demonstrate the OGD-RBM on a set of multi-category and binary classification problems for data sets having varying degrees of class-imbalance. We first apply the OGD-RBM algorithm on the multi-class MNIST dataset to characterize the network evolution. We demonstrate that the online generative phase converges to a stable, concise network architecture, wherein individual neurons are inherently discriminative to the class labels despite unsupervised training. We then benchmark OGD-RBM performance to other machine learning, neural network and ClassRBM techniques for credit scoring applications using 3 public non-stationary two-class credit datasets with varying degrees of class-imbalance. We report that OGD-RBM improves accuracy by 2.5-3% over batch learning techniques while requiring at least 24%-70% fewer neurons and fewer training samples. This online generative training approach can be extended greedily to multiple layers for training Deep Belief Networks in non-stationary data mining applications without the need for a priori fixed architectures.
Tasks
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02043v1
PDF	http://arxiv.org/pdf/1803.02043v1.pdf
PWC	https://paperswithcode.com/paper/online-deep-learning-growing-rbm-on-the-fly
Repo
Framework

Sentimental Content Analysis and Knowledge Extraction from News Articles


Title	Sentimental Content Analysis and Knowledge Extraction from News Articles
Authors	Mohammad Kamel, Neda Keyvani, Hadi Sadoghi Yazdi
Abstract	In web era, since technology has revolutionized mankind life, plenty of data and information are published on the Internet each day. For instance, news agencies publish news on their websites all over the world. These raw data could be an important resource for knowledge extraction. These shared data contain emotions (i.e., positive, neutral or negative) toward various topics; therefore, sentimental content extraction could be a beneficial task in many aspects. Extracting the sentiment of news illustrates highly valuable information about the events over a period of time, the viewpoint of a media or news agency to these events. In this paper an attempt is made to propose an approach for news analysis and extracting useful knowledge from them. Firstly, we attempt to extract a noise robust sentiment of news documents; therefore, the news associated to six countries: United State, United Kingdom, Germany, Canada, France and Australia in 5 different news categories: Politics, Sports, Business, Entertainment and Technology are downloaded. In this paper we compare the condition of different countries in each 5 news topics based on the extracted sentiments and emotional contents in news documents. Moreover, we propose an approach to reduce the bulky news data to extract the hottest topics and news titles as a knowledge. Eventually, we generate a word model to map each word to a fixed-size vector by Word2Vec in order to understand the relations between words in our collected news database.
Tasks
Published	2018-08-09
URL	http://arxiv.org/abs/1808.03027v1
PDF	http://arxiv.org/pdf/1808.03027v1.pdf
PWC	https://paperswithcode.com/paper/sentimental-content-analysis-and-knowledge
Repo
Framework

Matrix Factorization Equals Efficient Co-occurrence Representation


Title	Matrix Factorization Equals Efficient Co-occurrence Representation
Authors	Farhan Khawar, Nevin L. Zhang
Abstract	Matrix factorization is a simple and effective solution to the recommendation problem. It has been extensively employed in the industry and has attracted much attention from the academia. However, it is unclear what the low-dimensional matrices represent. We show that matrix factorization can actually be seen as simultaneously calculating the eigenvectors of the user-user and item-item sample co-occurrence matrices. We then use insights from random matrix theory (RMT) to show that picking the top eigenvectors corresponds to removing sampling noise from user/item co-occurrence matrices. Therefore, the low-dimension matrices represent a reduced noise user and item co-occurrence space. We also analyze the structure of the top eigenvector and show that it corresponds to global effects and removing it results in less popular items being recommended. This increases the diversity of the items recommended without affecting the accuracy.
Tasks
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09371v1
PDF	http://arxiv.org/pdf/1808.09371v1.pdf
PWC	https://paperswithcode.com/paper/matrix-factorization-equals-efficient-co
Repo
Framework

Exemplar-based synthesis of geology using kernel discrepancies and generative neural networks


Title	Exemplar-based synthesis of geology using kernel discrepancies and generative neural networks
Authors	Shing Chan, Ahmed H. Elsheikh
Abstract	We propose a framework for synthesis of geological images based on an exemplar image. We synthesize new realizations such that the discrepancy in the patch distribution between the realizations and the exemplar image is minimized. Such discrepancy is quantified using a kernel method for two-sample test called maximum mean discrepancy. To enable fast synthesis, we train a generative neural network in an offline phase to sample realizations efficiently during deployment, while also providing a parametrization of the synthesis process. We assess the framework on a classical binary image representing channelized subsurface reservoirs, finding that the method reproduces the visual patterns and spatial statistics (image histogram and two-point probability functions) of the exemplar image.
Tasks
Published	2018-09-20
URL	http://arxiv.org/abs/1809.07748v2
PDF	http://arxiv.org/pdf/1809.07748v2.pdf
PWC	https://paperswithcode.com/paper/exemplar-based-synthesis-of-geology-using
Repo
Framework

Deeper Interpretability of Deep Networks


Title	Deeper Interpretability of Deep Networks
Authors	Tian Xu, Jiayu Zhan, Oliver G. B. Garrod, Philip H. S. Torr, Song-Chun Zhu, Robin A. A. Ince, Philippe G. Schyns
Abstract	Deep Convolutional Neural Networks (CNNs) have been one of the most influential recent developments in computer vision, particularly for categorization. There is an increasing demand for explainable AI as these systems are deployed in the real world. However, understanding the information represented and processed in CNNs remains in most cases challenging. Within this paper, we explore the use of new information theoretic techniques developed in the field of neuroscience to enable novel understanding of how a CNN represents information. We trained a 10-layer ResNet architecture to identify 2,000 face identities from 26M images generated using a rigorously controlled 3D face rendering model that produced variations of intrinsic (i.e. face morphology, gender, age, expression and ethnicity) and extrinsic factors (i.e. 3D pose, illumination, scale and 2D translation). With our methodology, we demonstrate that unlike human’s network overgeneralizes face identities even with extreme changes of face shape, but it is more sensitive to changes of texture. To understand the processing of information underlying these counterintuitive properties, we visualize the features of shape and texture that the network processes to identify faces. Then, we shed a light into the inner workings of the black box and reveal how hidden layers represent these features and whether the representations are invariant to pose. We hope that our methodology will provide an additional valuable tool for interpretability of CNNs.
Tasks
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07807v2
PDF	http://arxiv.org/pdf/1811.07807v2.pdf
PWC	https://paperswithcode.com/paper/deeper-interpretability-of-deep-networks
Repo
Framework

Learning Feature Representations for Keyphrase Extraction


Title	Learning Feature Representations for Keyphrase Extraction
Authors	Corina Florescu, Wei Jin
Abstract	In supervised approaches for keyphrase extraction, a candidate phrase is encoded with a set of hand-crafted features and machine learning algorithms are trained to discriminate keyphrases from non-keyphrases. Although the manually-designed features have shown to work well in practice, feature engineering is a difficult process that requires expert knowledge and normally does not generalize well. In this paper, we present SurfKE, a feature learning framework that exploits the text itself to automatically discover patterns that keyphrases exhibit. Our model represents the document as a graph and automatically learns feature representation of phrases. The proposed model obtains remarkable improvements in performance over strong baselines.
Tasks	Feature Engineering
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01768v1
PDF	http://arxiv.org/pdf/1801.01768v1.pdf
PWC	https://paperswithcode.com/paper/learning-feature-representations-for
Repo
Framework

Non-Line-of-Sight Reconstruction using Efficient Transient Rendering


Title	Non-Line-of-Sight Reconstruction using Efficient Transient Rendering
Authors	Julian Iseringhausen, Matthias B. Hullin
Abstract	Being able to see beyond the direct line of sight is an intriguing prospective and could benefit a wide variety of important applications. Recent work has demonstrated that time-resolved measurements of indirect diffuse light contain valuable information for reconstructing shape and reflectance properties of objects located around a corner. In this paper, we introduce a novel reconstruction scheme that, by design, produces solutions that are consistent with state-of-the-art physically-based rendering. Our method combines an efficient forward model (a custom renderer for time-resolved three-bounce indirect light transport) with an optimization framework to reconstruct object geometry in an analysis-by-synthesis sense. We evaluate our algorithm on a variety of synthetic and experimental input data, and show that it gracefully handles uncooperative scenes with high levels of noise or non-diffuse material reflectance.
Tasks
Published	2018-09-21
URL	https://arxiv.org/abs/1809.08044v2
PDF	https://arxiv.org/pdf/1809.08044v2.pdf
PWC	https://paperswithcode.com/paper/non-line-of-sight-reconstruction-using
Repo
Framework

Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery


Title	Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
Authors	Yichen Wu, Yair Rivenson, Yibo Zhang, Zhensong Wei, Harun Gunaydin, Xing Lin, Aydogan Ozcan
Abstract	Holography encodes the three dimensional (3D) information of a sample in the form of an intensity-only recording. However, to decode the original sample image from its hologram(s), auto-focusing and phase-recovery are needed, which are in general cumbersome and time-consuming to digitally perform. Here we demonstrate a convolutional neural network (CNN) based approach that simultaneously performs auto-focusing and phase-recovery to significantly extend the depth-of-field (DOF) in holographic image reconstruction. For this, a CNN is trained by using pairs of randomly de-focused back-propagated holograms and their corresponding in-focus phase-recovered images. After this training phase, the CNN takes a single back-propagated hologram of a 3D sample as input to rapidly achieve phase-recovery and reconstruct an in focus image of the sample over a significantly extended DOF. This deep learning based DOF extension method is non-iterative, and significantly improves the algorithm time-complexity of holographic image reconstruction from O(nm) to O(1), where n refers to the number of individual object points or particles within the sample volume, and m represents the focusing search space within which each object point or particle needs to be individually focused. These results highlight some of the unique opportunities created by data-enabled statistical image reconstruction methods powered by machine learning, and we believe that the presented approach can be broadly applicable to computationally extend the DOF of other imaging modalities.
Tasks	Image Reconstruction
Published	2018-03-21
URL	http://arxiv.org/abs/1803.08138v1
PDF	http://arxiv.org/pdf/1803.08138v1.pdf
PWC	https://paperswithcode.com/paper/extended-depth-of-field-in-holographic-image
Repo
Framework

Effective Cloud Detection and Segmentation using a Gradient-Based Algorithm for Satellite Imagery; Application to improve PERSIANN-CCS


Title	Effective Cloud Detection and Segmentation using a Gradient-Based Algorithm for Satellite Imagery; Application to improve PERSIANN-CCS
Authors	Negin Hayatbini, Kuo-lin Hsu, Soroosh Sorooshian, Yunji Zhang, Fuqing Zhang
Abstract	Being able to effectively identify clouds and monitor their evolution is one important step toward more accurate quantitative precipitation estimation and forecast. In this study, a new gradient-based cloud-image segmentation technique is developed using tools from image processing techniques. This method integrates morphological image gradient magnitudes to separable cloud systems and patches boundaries. A varying scale-kernel is implemented to reduce the sensitivity of image segmentation to noise and capture objects with various finenesses of the edges in remote-sensing images. The proposed method is flexible and extendable from single- to multi-spectral imagery. Case studies were carried out to validate the algorithm by applying the proposed segmentation algorithm to synthetic radiances for channels of the Geostationary Operational Environmental Satellites (GOES-R) simulated by a high-resolution weather prediction model. The proposed method compares favorably with the existing cloud-patch-based segmentation technique implemented in the PERSIANN-CCS (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Network - Cloud Classification System) rainfall retrieval algorithm. Evaluation of event-based images indicates that the proposed algorithm has potential to improve rain detection and estimation skills with an average of more than 45% gain comparing to the segmentation technique used in PERSIANN-CCS and identifying cloud regions as objects with accuracy rates up to 98%.
Tasks	Cloud Detection, Semantic Segmentation
Published	2018-09-27
URL	http://arxiv.org/abs/1809.10801v1
PDF	http://arxiv.org/pdf/1809.10801v1.pdf
PWC	https://paperswithcode.com/paper/effective-cloud-detection-and-segmentation
Repo
Framework

Dynamic Control Flow in Large-Scale Machine Learning


Title	Dynamic Control Flow in Large-Scale Machine Learning
Authors	Yuan Yu, Martín Abadi, Paul Barham, Eugene Brevdo, Mike Burrows, Andy Davis, Jeff Dean, Sanjay Ghemawat, Tim Harley, Peter Hawkins, Michael Isard, Manjunath Kudlur, Rajat Monga, Derek Murray, Xiaoqiang Zheng
Abstract	Many recent machine learning models rely on fine-grained dynamic control flow for training and inference. In particular, models based on recurrent neural networks and on reinforcement learning depend on recurrence relations, data-dependent conditional execution, and other features that call for dynamic control flow. These applications benefit from the ability to make rapid control-flow decisions across a set of computing devices in a distributed system. For performance, scalability, and expressiveness, a machine learning system must support dynamic control flow in distributed and heterogeneous environments. This paper presents a programming model for distributed machine learning that supports dynamic control flow. We describe the design of the programming model, and its implementation in TensorFlow, a distributed machine learning system. Our approach extends the use of dataflow graphs to represent machine learning models, offering several distinctive features. First, the branches of conditionals and bodies of loops can be partitioned across many machines to run on a set of heterogeneous devices, including CPUs, GPUs, and custom ASICs. Second, programs written in our model support automatic differentiation and distributed gradient computations, which are necessary for training machine learning models that use control flow. Third, our choice of non-strict semantics enables multiple loop iterations to execute in parallel across machines, and to overlap compute and I/O operations. We have done our work in the context of TensorFlow, and it has been used extensively in research and production. We evaluate it using several real-world applications, and demonstrate its performance and scalability.
Tasks
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01772v1
PDF	http://arxiv.org/pdf/1805.01772v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-control-flow-in-large-scale-machine
Repo
Framework