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

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

Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. These boundaries are preserved by retaining substantially more frequency content from the original image than other existing techniques. Our method exploits features of color and luminance, is simple to implement, and is computationally efficient. We compare our algorithm to five state-of-the-art salient region detection methods with a frequency domain analysis, ground truth, and a salient object segmentation application. Our method outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.

/pdf/frequency-tuned-salient-region-detection-4po18ylvds.pdf

Frequency-tuned salient region detection

Automatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient object detection algorithm, which simultaneously evaluates global contrast differences and spatial weighted coherence scores. The proposed algorithm is simple, efficient, naturally multi-scale, and produces full-resolution, high-quality saliency maps. These saliency maps are further used to initialize a novel iterative version of GrabCut, namely SaliencyCut, for high quality unsupervised salient object segmentation. We extensively evaluated our algorithm using traditional salient object detection datasets, as well as a more challenging Internet image dataset. Our experimental results demonstrate that our algorithm consistently outperforms 15 existing salient object detection and segmentation methods, yielding higher precision and better recall rates. We also show that our algorithm can be used to efficiently extract salient object masks from Internet images, enabling effective sketch-based image retrieval (SBIR) via simple shape comparisons. Despite such noisy internet images, where the saliency regions are ambiguous, our saliency guided image retrieval achieves a superior retrieval rate compared with state-of-the-art SBIR methods, and additionally provides important target object region information.

https://mmcheng.net/mftp/SalObj/PosterSaliency.pdf

Global contrast based salient region detection

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Filter decomposition approach has been presented for multichannel blind deconvolution of non-minimum phase systems [12] In this paper, we present a flexible cascade structure by decomposing the demixing filter into a casual finite impulse response (FIR) filter and an anti-causal scalar FIR filter Subsequently, we develop the natural gradient algorithms for both filters Computer simulations show good learning performance of this method

Multichannel blind deconvolution of non-minimum phase system using cascade structure

This paper deals with the monotone homotopy methods for solving the system of nonlinear equations. In Sect. 2 the homotopy with a distancemonotone homotopy path is discussed and it is proved that a homotopy with a given structure has a distance monotone homotopy path under some regular conditions. Then two structure-variable homotopy algorithms called local straighten-up method and global straighten-up method are developed to approximate the optimal homotopy, and an adaptive step-size control strategy for these algorithms is proposed respectively. A new method for analyzing the convergence is presented, which is based on the geometrical properties of the algorithm. Then the convergence of the algorithm is proved under certain regular conditions. Finally two numerical examples are given to illustrate the effectiveness of the above two algorithms.

Optimal homotopy methods for solving nonlinear systems

The goal of Sketch-Based Image Retrieval (SBIR) is using free-hand sketches to retrieve images of the same category from a natural image gallery. However, SBIR requires all test categories to be seen during training, which cannot be guaranteed in real-world applications. So we investigate more challenging Zero-Shot SBIR (ZS-SBIR), in which test categories do not appear in the training stage. After realizing that sketches mainly contain structure information while images contain additional appearance information, we attempt to achieve structure-aware retrieval via asymmetric disentanglement.For this purpose, we propose our STRucture-aware Asymmetric Disentanglement (STRAD) method, in which image features are disentangled into structure features and appearance features while sketch features are only projected to structure space. Through disentangling structure and appearance space, bi-directional domain translation is performed between the sketch domain and the image domain. Extensive experiments demonstrate that our STRAD method remarkably outperforms state-of-the-art methods on three large-scale benchmark datasets.

Zero-Shot Sketch-Based Image Retrieval with Structure-aware Asymmetric Disentanglement

This paper proposes a novel generative model for natural image representation and scene classification. Given a natural image, it is decomposed with learned holistic basis called scene gist components. This gist representation is a global and adaptive image descriptor, generatively including most essential information related to visual perception. Meanwhile prior knowledge for scene category is integrated in the generative model to interpret the newly input image. To validate the efficiency of the scene gist representation, a simple nonparametric scene classification algorithm is developed based on minimizing the scene reconstruction error. Finally comparison with other scene classification algorithm is given to show the higher performance of the proposed model.

/pdf/scene-gist-a-holistic-generative-model-of-natural-image-7vkyeh6a75.pdf

Scene gist: a holistic generative model of natural image

In this paper, we propose an electrocardiogram (ECG) pattern classification method for 12-lead ECG using Semi-supervised Discriminant Analysis (SDA). The feature of 12-lead ECG signal is firstly extracted by wavelet transformation (WT). SDA is used to find a projection which projects the WT feature space into low dimension feature space for ECG pattern classification. The semi-supervised learning approach is used to cluster unlabeled data. Finally the SVM classifier is applied to multi-classification experiments. The experiment results show the proposed method can achieve high classification accuracy. When the labeled data is insufficient, the proposed method also demonstrates good generalization ability.

Liqing Zhang

Papers

Multichannel blind deconvolution of non-minimum phase system using cascade structure

Optimal homotopy methods for solving nonlinear systems

Zero-Shot Sketch-Based Image Retrieval with Structure-aware Asymmetric Disentanglement

Scene gist: a holistic generative model of natural image

A 12-lead clinical ECG classification method based on Semi-supervised Discriminant Analysis