Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Phd by thesis

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

IEEE Transactions on Pattern Analysis and Machine Intelligence

Collecting large clean-distorted training image pairs in real world is non-trivial, which seriously limits the practical applications of these supervised learning based image restoration (IR) methods. Previous works attempt to address this problem by leveraging unsupervised learning technologies to alleviate the dependency for paired training samples. However, these methods typically suffer from unsatisfactory textures synthesis due to the lack of clean image supervision. Compared with purely unsupervised solution, the under-explored scheme with Few-Shot clean images (FS-IR) is more feasible to tackle this challenging real Image Restoration task. In this paper, we are the first to investigate the few-shot real image restoration and propose a Distortion-Relation guided Transfer Learning (termed as DRTL) framework. DRTL assigns a knowledge graph to capture the distortion relation between auxiliary tasks (i.e., synthetic distortions) and target tasks (i.e., real distortions with few images), and then adopt a gradient weighting strategy to guide the knowledge transfer from auxiliary task to target task. In this way, DRTL could quickly learn the most relevant knowledge from the prior distortions for target distortion. We instantiate DRTL integrated with pre-training and meta-learning pipelines as an embodiment to realize a distortion-relation aware FS-IR. Extensive experiments on multiple benchmarks demonstrate the effectiveness of DRTL on few-shot real image restoration.

Few-Shot Real Image Restoration via Distortion-Relation Guided Transfer Learning

A method for processing an image divided into blocks of pixels is disclosed. The method comprises the steps of:
 detecting, for each block, a largest sub-block whose pixels have an equal luminance value; identifying, for each block, if the detected largest sub-block is or is not a natural texture; determining, for each block, a block blockiness level on the basis of the number of pixels within the detected largest sub-block and on the basis of the identification step; and processing the image on the basis of the block blockiness levels.

Method for processing an image

PROBLEM TO BE SOLVED: To provide a method of encoding a bit sequence capable of achieving compact encoding SOLUTION: The method of encoding a bit sequence includes: a step of generating, for each run of "1" included in the bit sequence, a unary representation of a length of the each run of "1"; a step of generating a first sequence by concatenating the generated unary representations of lengths of respective runs of "1"; a step of generating, for each run of "0" included in the bit sequence, a unary representation of length of each run of "0"; a step of generating a second sequence by concatenating the generated unary representations of lengths of respective runs of "0"; and a step of bit plane encoding the generated first and second sequences COPYRIGHT: (C)2010,JPO&INPIT

Method and device for encoding bit sequence

In land seismic data processing, the first arrivals are often picked to image the near surface by applying a traveltime inversion method for statics corrections. In many areas, however, the first arrivals of a shot gather exhibit a pattern of shingling: the first arrivals quickly disappear over offset and then another branch nearly parallel to the previous one appears with a constant time shift, and the pattern may be repeated further. It is difficult to image the near surface with this type of data. We develop a method based on the convolutional neural network (CNN) for automatically detecting the shingling features directly from 3D seismic data. After detecting, dedicated strategies for picking and near surface imaging can be applied to the targeted shots to improve the traveltime tomographic results. This method contains two steps: training and prediction. First, the CNN is trained with the human-labeled seismic data, where each pixel is labeled as either shingling or non-shingling. After training, the CNN predicts shingling probabilities at every shot in the data. The test results on both synthetic and field data suggest that the CNN predicts shingling features with high accuracy. With the capability of emulating human experience and evolving via training with new datasets, CNN technology shows great promise for automating seismic data processing and site characterization.

Detection of the near surface velocity reveal with the convolutional neural network

Recently, adaptive graph convolutional network based traffic prediction methods, learning a latent graph structure from traffic data via various attention-based mechanisms, have achieved impressive performance. However, they are still limited to find a better description of spatial relationships between traffic conditions due to: (1) ignoring the prior of the observed topology of the road network; (2) neglecting the presence of negative spatial relationships; and (3) lacking investigation on uncertainty of the graph structure. In this paper, we propose a Bayesian Graph Convolutional Network (BGCN) framework to alleviate these issues. Under this framework, the graph structure is viewed as a random realization from a parametric generative model, and its posterior is inferred using the observed topology of the road network and traffic data. Specifically, the parametric generative model is comprised of two parts: (1) a constant adjacency matrix which discovers potential spatial relationships from the observed physical connections between roads using a Bayesian approach; (2) a learnable adjacency matrix that learns a global shared spatial correlations from traffic data in an end-to-end fashion and can model negative spatial correlations. The posterior of the graph structure is then approximated by performing Monte Carlo dropout on the parametric graph structure. We verify the effectiveness of our method on five real-world datasets, and the experimental results demonstrate that BGCN attains superior performance compared with state-of-the-art methods.

Zhibo Chen

Papers

Few-Shot Real Image Restoration via Distortion-Relation Guided Transfer Learning

Method for processing an image

Method and device for encoding bit sequence

Detection of the near surface velocity reveal with the convolutional neural network

Bayesian Graph Convolutional Network for Traffic Prediction