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

This paper proposes a computational model for visual perception: the visual pathway is considered as a functional process of dimensionality reduction for input data, that is, to search for the intrinsic dimensionality of natural scene images. This model is hierarchically constructed, and final leads to the formation of a low-dimensional space called perceptual manifold. Further analysis of the perceptual manifold reveals that scene images which share similar perceptual similarities stay nearby in the manifold space, and the dimensions of the space could describe the spatial layout of scenes, which are like the degree of naturalness, openness supervised trained in (Oliva, A., and Torralba, A. Int. J. Comput. Vis. 42 (2001) 145–175). Moreover, the implementation of scene retrieval task validates the topographic property of the perceptual manifold space.

/pdf/a-hierarchial-model-for-visual-perception-4s6wsbyw4t.pdf

A Hierarchial Model for Visual Perception

Simple Summary It is understood that 10-HDA is a medium-chain fatty acid derivative containing an ω-hydroxy group, which is one of the main active components in royal jelly. Furthermore, 10-HDA has been proven to possess various physiological and pharmacological activities, including antibiotic, immunomodulatory, and antioxidant activity, etc. However, few studies have shown the role of 10-HDA in broiler chickens. This research assessed the impacts of 10-HDA on growth performance, antioxidant capacity, and the immunity of broiler chickens. The findings demonstrated that a diet supplemented with 40 mg/kg 10-HDA apparently elevated the average daily gain, immunocompetence, and antioxidant capacity of broiler chickens. It is concluded that the growth performance of broiler chickens is greatly enhanced by 10-HDA, and that 10-HDA will have broad application prospects as a new feed additive in animal production. Abstract The purposes of this study were to explore the potential possibility of 10-hydroxy-trans-2-decenoic acid (10-HDA) use in feeding broiler chickens. A total of 216 healthy 1-day-old chicks were divided into 2 treatments at random (diets supplemented with 0 or 40 mg/kg 10-HDA, respectively) with 6 replicates of 18 birds each, and were then reared for 42 days. The results found that a diet supplemented with 10-HDA significantly increased average daily gain of broiler chickens in d 22~42 and d 0~42. Compared with the control group, dietary inclusion of 10-HDA markedly increased the serum concentrations of immunoglobulin (Ig) G at d 21, as well as IgM and interleukin (IL)-10 at d 42, while decreasing the levels of tumor necrosis factor (TNF)-α at d 21, as well as IL-6, TNF-α, and IL-1β at d 42. Furthermore, broiler chickens fed a diet with 10-HDA had a higher (p < 0.05) serum activity of superoxide dismutase at d 42. Additionally, serum malondialdehyde content also decreased notably at d 21 and d 42. These results made it clear that 10-HDA increased the growth performance of broiler chickens, possibly by enhancing immune function and antioxidant capacity.

/pdf/10-hydroxy-trans-2-decenoic-acid-a-new-potential-feed-34t0tiyw.pdf

10-Hydroxy-trans-2-decenoic Acid, a New Potential Feed Additive for Broiler Chickens to Improve Growth Performance

Visual perception of transformation invariance, such as translation, rotation and scaling, is one of the important functions of processing visual information in the Brain. To simulate this perception property, we propose a computational model for perception of transformation. First, we briefly introduce the transformation-invariant basis functions learned from natural scenes using Independent Component Analysis (ICA). Then we use these basis functions to construct the perceptual model. By using the correlation coefficients of two neural responses as the measure of transformation-invariance, the model is able to perform the task of perception of transformation. Comparisons with Bilinear Sparse Coding presented by Grimes and Rao and Topo-ICA by Hayvarinen show that the proposed perceptual model has some advantages such as simple to implement and more robust to transformation invariance. Computer simulation results demonstrate that the model successfully simulates the mechanism for visual perception of transformation invariance.

/pdf/perception-of-transformation-invariance-in-the-visual-4uktu7irbb.pdf

Perception of transformation-invariance in the visual pathway

Visual perception of rotation is one of important functions of processing information in the visual pathway. To simulate the mechanism, we propose a model for perception of rotation. First, we briefly introduce the rotation-invariant basis functions learned from natural scenes using independent component analysis (ICA). We used these basis functions to construct the perceptual model. By using the correlation coefficients of two neural responses as the measure of rotation-invariance, our model can perform the task of perception of rotating angles. Computer simulation results show that the present model is able to perceive rotation- invariance and successfully perceive the relative angles of rotating patches.

/pdf/computational-model-for-rotation-invariant-perception-2h3p8z10gc.pdf

Computational Model for Rotation-Invariant Perception

This paper presents a novel topic model named Affine Invariant Topic Model(AITM) for generic object recognition Abandoning the “bag of words” assumption in traditional topic models, AITM incorporates spatial structure into traditional LDA AITM extends LDA by modeling visual words with latent affine transformations as well as latent topics, treating topics as different parts of objects and assuming a common affine transformation of visual words given a certain topic MCMC is employed to make inference for latent variables, MCMC-EM algorithm is used to parameter estimation, and Bayesian decision rule is used to perform classification Experiments on two challenging data sets demonstrate the efficiency of AITM.

Liqing Zhang

Papers

A Hierarchial Model for Visual Perception

10-Hydroxy-trans-2-decenoic Acid, a New Potential Feed Additive for Broiler Chickens to Improve Growth Performance

Perception of transformation-invariance in the visual pathway

Computational Model for Rotation-Invariant Perception

Affine invariant topic model for generic object recognition