arXiv subjects

Xiaoxiao Sun

Publications and source records attributed to Xiaoxiao Sun.

41 records · Page 3Linked to original sources

arXiv2019

Dissecting Person Re-identification from the Viewpoint of Viewpoint

Variations in visual factors such as viewpoint, pose, illumination and background, are usually viewed as important challenges in person re-identification (re-ID). In spite of acknowledging these factors to be influential, quantitative studies on how they affect a re-ID system are still lacking. To derive insights in this scientific campaign, this paper makes an early attempt in studying a particular factor, viewpoint. We narrow the viewpoint problem down to the pedestrian rotation angle to obtain focused conclusions. In this regard, this paper makes two contributions to the community. First, we introduce a large-scale synthetic data engine, PersonX. Composed of hand-crafted 3D person models, the salient characteristic of this engine is "controllable". That is, we are able to synthesize pedestrians by setting the visual variables to arbitrary values. Second, on the 3D data engine, we quantitatively analyze the influence of pedestrian rotation angle on re-ID accuracy. Comprehensively, the person rotation angles are precisely customized from 0 to 360, allowing us to investigate its effect on the training, query, and gallery sets. Extensive experiment helps us have a deeper understanding of the fundamental problems in person re-ID. Our research also provides useful insights for dataset building and future practical usage, e.g., a person of a side view makes a better query.

cs.CV↗

arXiv2019

Optimal Penalized Function-on-Function Regression under a Reproducing Kernel Hilbert Space Framework

Many scientific studies collect data where the response and predictor variables are both functions of time, location, or some other covariate. Understanding the relationship between these functional variables is a common goal in these studies. Motivated from two real-life examples, we present in this paper a function-on-function regression model that can be used to analyze such kind of functional data. Our estimator of the 2D coefficient function is the optimizer of a form of penalized least squares where the penalty enforces a certain level of smoothness on the estimator. Our first result is the Representer Theorem which states that the exact optimizer of the penalized least squares actually resides in a data-adaptive finite dimensional subspace although the optimization problem is defined on a function space of infinite dimensions. This theorem then allows us an easy incorporation of the Gaussian quadrature into the optimization of the penalized least squares, which can be carried out through standard numerical procedures. We also show that our estimator achieves the minimax convergence rate in mean prediction under the framework of function-on-function regression. Extensive simulation studies demonstrate the numerical advantages of our method over the existing ones, where a sparse functional data extension is also introduced. The proposed method is then applied to our motivating examples of the benchmark Canadian weather data and a histone regulation study.

stat.ME↗

arXiv2019

Image Recognition of Tea Leaf Diseases Based on Convolutional Neural Network

In order to identify and prevent tea leaf diseases effectively, convolution neural network (CNN) was used to realize the image recognition of tea disease leaves. Firstly, image segmentation and data enhancement are used to preprocess the images, and then these images were input into the network for training. Secondly, to reach a higher recognition accuracy of CNN, the learning rate and iteration numbers were adjusted frequently and the dropout was added properly in the case of over-fitting. Finally, the experimental results show that the recognition accuracy of CNN is 93.75%, while the accuracy of SVM and BP neural network is 89.36% and 87.69% respectively. Therefore, the recognition algorithm based on CNN is better in classification and can improve the recognition efficiency of tea leaf diseases effectively.

cs.CV↗

arXiv2018

Learning from Web Data: the Benefit of Unsupervised Object Localization

Annotating a large number of training images is very time-consuming. In this background, this paper focuses on learning from easy-to-acquire web data and utilizes the learned model for fine-grained image classification in labeled datasets. Currently, the performance gain from training with web data is incremental, like a common saying "better than nothing, but not by much". Conventionally, the community looks to correcting the noisy web labels to select informative samples. In this work, we first systematically study the built-in gap between the web and standard datasets, i.e. different data distributions between the two kinds of data. Then, in addition to using web labels, we present an unsupervised object localization method, which provides critical insights into the object density and scale in web images. Specifically, we design two constraints on web data to substantially reduce the difference of data distributions for the web and standard datasets. First, we present a method to control the scale, localization and number of objects in the detected region. Second, we propose to select the regions containing objects that are consistent with the web tag. Based on the two constraints, we are able to process web images to reduce the gap, and the processed web data is used to better assist the standard dataset to train CNNs. Experiments on several fine-grained image classification datasets confirm that our method performs favorably against the state-of-the-art methods.

cs.CV↗

arXiv2018

Development and validation of Critical Thinking Disposition Inventory for Chinese medical college students (CTDI-M)

PURPOSE: Critical thinkers in medical context must be not only "able" but also "willing" to think critically. To develop and conduct psychometric testing of Critical Thinking Disposition Inventory which measure the critical thinking disposition of Chinese medical college students. METHODS: The study was conducted in two stages: (a) item generation and exploratory factor analysis (EFA) and (b) testing of psychometric properties (construct validity, split-half reliability and Cronbach's alpha, and test-retest reliability. The subjects were composed of 441 undergraduate medical and nursing students from a medical university in China. Test-retest reliability of the instrument was determined at two-week interval. Data was analyzed with SPSS13.0. RESULTS: Preliminary 264 items were obtained using an open-ended questionnaire; from which 61 items were reviewed through half open-ended questionnaire, and finally 18 items were chosen. Eighteen final items were sorted into 3 factors, which were identified as "Open-mindedness ", "Systematicity/analyticity" and "Truth seeking". The cumulative percent of variance was 57.66%. The Cronbach's alpha was 0.924 and the factors' alphas ranged from 0.824-0.862. Correlational analysis indicated moderate to high correlations between the subscales and total scores of the CTDI-CM. Our results indicated that open-mindedness and systematicity/analyticity were higher for medical students than nursing students. CONCLUSIONS: This study conducted in a Chinese medical college student population demonstrated a reliable and valid instrument for clinical thinking disposition, which measured motivation and cognitive components. The effect of enrollment year and major on the profiles of critical thinking dispositions was identified, emphasizing the importance of applying specialized teaching to students of different majors.

physics.ed-ph↗