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

RGB-D object detection has achieved significant advance, because depth provides complementary geometric information to RGB images. Considering depth images are unavailable in some scenarios, we focus on depth privileged object detection in indoor scenes, where the depth images are only available in the training phase. Under this setting, one prevalent research line is modality hallucination, in which depth image and depth feature are the common choices for hallucinating. In contrast, we choose to hallucinate depth deformation, which is explicit geometric information and efficient to hallucinate. Specifically, we employ the deformable convolution layer with augmented offsets as our deformation module and regard the offsets as geometric deformation, because the offsets enable flexibly sampling over the object and transforming to a canonical shape for ease of detection. In addition, we design a quality-based mechanism to avoid negative transfer of depth deformation. Experimental results and analyses on NYUDv2 and SUN RGB-D demonstrate the effectiveness of our method against the state-of-the-art methods for depth privileged object detection.

Depth Privileged Object Detection in Indoor Scenes via Deformation Hallucination.

Networked-guarantee loans may cause systemic risk related concern for the government and banks in China. The prediction of the default of enterprise loans is a typical machine learning based classification problem, and the networked guarantee makes this problem very difficult to solve. As we know, a complex network is usually stored and represented by an adjacency matrix. It is a high-dimensional and sparse matrix, whereas machine-learning methods usually need lowdimensional dense feature representations. Therefore, in this paper, we propose a binary higher-order network embedding method to learn the low-dimensional representations of a guarantee network. We first set vertices of this heterogeneous economic network by binary roles (guarantor and guarantee), and then define high-order adjacent measures based on their roles and economic domain knowledge. Afterwards, we design a penalty parameter in the objective function to balance the importance of network structure and adjacency. We optimize it by negative sampling based gradient descent algorithms, which solve the limitation of stochastic gradient descent on weighted edges without compromising efficiency. Finally, we test our proposed method on three real-world network datasets. The result shows that this method outperforms other start-of-the-art algorithms for both classification accuracy and robustness, especially in a guarantee network.

BHONEM: Binary High-Order Network Embedding Methods for Networked-Guarantee Loans

An improvement to the Probabilistic Neural Network (PNN) is presented that overcomes two weaknesses of the original model. In the new model, due to the fact that each neuron uses its own Gaussian kernel function, a better generalization ability is achieved by the means of stretching and rotation leading to the Rotated Kernel Probabilistic Neural Network (RKPNN). Furthermore, an algorithm is presented that calculates automatically the kernel parameters of each Gaussian function. The covariance matrices will be subdivided into two other matrices R and S that are calculated separately. This training is slower than that of the original PNN, but in its complexity comparable with other classification methods. A real-world example finally prooves that the proposed model shows good generalization capacity with similar or even slightly better results than other approaches.

Independent residual analysis for temporally correlated signals

In this work, we introduce the PPTLens system to convert sketch images captured by smart phones to digital flowcharts in PowerPoint. Different from existing sketch recognition system, which is based on hand-drawn strokes, PPTLens enables users to use sketch images as inputs directly. It's more challenging since strokes extracted from sketch images might not only be very messy, but also without temporal information of the drawings. To implement the 'Image to Object' (I2O) scenario, we propose a novel sketch image recognition framework, including an effective stroke extraction strategy and a novel offline sketch parsing algorithm. By enabling sketch images as inputs, our system makes flowchart/diagram production much more convenient and easier.

/pdf/pptlens-create-digital-objects-with-sketch-images-rih3ioczbj.pdf

PPTLens: Create Digital Objects with Sketch Images

This paper presents a novel image denoising framework using overcomplete topographic model. To adapt to the statistics of natural images, we impose both spareseness and topograpgic constraints on the denoising model. Based on the overcomplete topographic model, our denoising system improves the previous work on the following aspects: multi-category based sparse coding, adaptive learning, local normalization, lasso shrinkage function, and subset selection. A large number of simulations have been performed to show the performance of the modified model, demonstrating that the proposed model achieves better denoising performance.

Liqing Zhang

Papers

Depth Privileged Object Detection in Indoor Scenes via Deformation Hallucination.

BHONEM: Binary High-Order Network Embedding Methods for Networked-Guarantee Loans

Independent residual analysis for temporally correlated signals

PPTLens: Create Digital Objects with Sketch Images

Statistically Adaptive Image Denoising Based on Overcomplete Topographic Sparse Coding