The Experts below are selected from a list of 261 Experts worldwide ranked by ideXlab platform
Song-chun Zhu - One of the best experts on this subject based on the ideXlab platform.
-
a Generative Method for textured motion analysis and synthesis
European Conference on Computer Vision, 2002Co-Authors: Yizhou Wang, Song-chun ZhuAbstract:Natural scenes contain rich stochastic motion patterns which are characterized by the movement of a large number of small elements, such as falling snow, raining, flying birds, firework and waterfall. In this paper, we call these motion patterns textured motion and present a Generative Method that combines statistical models and algorithms from both texture and motion analysis. The Generative Method includes the following three aspects. 1). Photometrically, an image is represented as a superposition of linear bases in atomic decomposition using an overcomplete dictionary, such as Gabor or Laplacian. Such base representation is known to be generic for natural images, and it is low dimensional as the number of bases is often 100 times smaller than the number of pixels. 2). Geometrically, each moving element (called moveton), such as the individual snowflake and bird, is represented by a deformable template which is a group of several spatially adjacent bases. Such templates are learned through clustering. 3). Dynamically, the movetons are tracked through the image sequence by a stochastic algorithm maximizing a posterior probability. A classic second order Markov chain model is adopted for the motion dynamics. The sources and sinks of the movetons are modeled by birth and death maps. We adopt an EM-like stochastic gradient algorithm for inference of the hidden variables: bases, movetons, birth/death maps, parameters of the dynamics. The learned models are also verified through synthesizing random textured motion sequences which bear similar visual appearance with the observed sequences.
-
ECCV (1) - A Generative Method for Textured Motion: Analysis and Synthesis
Computer Vision — ECCV 2002, 2002Co-Authors: Yizhou Wang, Song-chun ZhuAbstract:Natural scenes contain rich stochastic motion patterns which are characterized by the movement of a large number of small elements, such as falling snow, raining, flying birds, firework and waterfall. In this paper, we call these motion patterns textured motion and present a Generative Method that combines statistical models and algorithms from both texture and motion analysis. The Generative Method includes the following three aspects. 1). Photometrically, an image is represented as a superposition of linear bases in atomic decomposition using an overcomplete dictionary, such as Gabor or Laplacian. Such base representation is known to be generic for natural images, and it is low dimensional as the number of bases is often 100 times smaller than the number of pixels. 2). Geometrically, each moving element (called moveton), such as the individual snowflake and bird, is represented by a deformable template which is a group of several spatially adjacent bases. Such templates are learned through clustering. 3). Dynamically, the movetons are tracked through the image sequence by a stochastic algorithm maximizing a posterior probability. A classic second order Markov chain model is adopted for the motion dynamics. The sources and sinks of the movetons are modeled by birth and death maps. We adopt an EM-like stochastic gradient algorithm for inference of the hidden variables: bases, movetons, birth/death maps, parameters of the dynamics. The learned models are also verified through synthesizing random textured motion sequences which bear similar visual appearance with the observed sequences.
-
A Generative Method for Textured Motion: Analysis and Synthesis
2002Co-Authors: Yizhou Wang, Song-chun ZhuAbstract:Natural scenes contain rich stochastic motion patterns which are characterized by the movement of a large number of small elements, such as falling snow, raining, flying birds, firework and waterfall. In this paper, we call these motion patterns textured motion and present a Generative Method that combines statistical models and algorithms from both texture and motion analysis. The Generative Method includes the following aspects. !). Photometrically, an image is represented as a superposition of linear bases in atomic decomposition using an over-comlete dictionary, such as Gabor or Laplacian. Such base representation is known to be generic for natural images, and it is low dimensional as the number of bases is often 100 times smaller than the number of pixels. 2). Geometricall, each moving element (called moveton), such as the individual snowflake and bird, is represented by a deformable template which is a group of several spatially adjacent bases. Such templates are learned through clustering. 3). Dynamically, the movetons are tracked through the image sequence by a stochastic algorithm maximizing a posterior probability. A classic second order Markov chain model is adopted for the motion of dynamics. The sources and sinks of the movetons are modeled by birth and death maps. We adopt an EM-like stochastic gradient algorithm for inference of the hidden variables: bases, movetons, birth/death maps, parameters of the dynamics. The learned models are also verified through synthesizing random textured motion sequences which bear similar visual appearances with the ovserved sequences.
J M Leiva - One of the best experts on this subject based on the ideXlab platform.
-
a Generative model approach for decoding in the visual event related potential based brain computer interface speller
Journal of Neural Engineering, 2010Co-Authors: S M M Martens, J M LeivaAbstract:There is a strong tendency towards discriminative approaches in brain–computer interface (BCI) research. We argue that Generative model-based approaches are worth pursuing and propose a simple Generative model for the visual ERP-based BCI speller which incorporates prior knowledge about the brain signals. We show that the proposed Generative Method needs less training data to reach a given letter prediction performance than the state of the art discriminative approaches.
-
A Generative model approach for decoding in the visual event-related potential-based brain–computer interface speller
Journal of neural engineering, 2010Co-Authors: S M M Martens, J M LeivaAbstract:There is a strong tendency towards discriminative approaches in brain–computer interface (BCI) research. We argue that Generative model-based approaches are worth pursuing and propose a simple Generative model for the visual ERP-based BCI speller which incorporates prior knowledge about the brain signals. We show that the proposed Generative Method needs less training data to reach a given letter prediction performance than the state of the art discriminative approaches.
Danny Z. Chen - One of the best experts on this subject based on the ideXlab platform.
-
Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation
arXiv: Computer Vision and Pattern Recognition, 2020Co-Authors: Hongxiao Wang, Hao Zheng, Jianxu Chen, Lin Yang, Yizhe Zhang, Danny Z. ChenAbstract:Automatic histopathology image segmentation is crucial to disease analysis. Limited available labeled data hinders the generalizability of trained models under the fully supervised setting. Semi-supervised learning (SSL) based on Generative Methods has been proven to be effective in utilizing diverse image characteristics. However, it has not been well explored what kinds of generated images would be more useful for model training and how to use such images. In this paper, we propose a new data guided Generative Method for histopathology image segmentation by leveraging the unlabeled data distributions. First, we design an image generation module. Image content and style are disentangled and embedded in a clustering-friendly space to utilize their distributions. New images are synthesized by sampling and cross-combining contents and styles. Second, we devise an effective data selection policy for judiciously sampling the generated images: (1) to make the generated training set better cover the dataset, the clusters that are underrepresented in the original training set are covered more; (2) to make the training process more effective, we identify and oversample the images of "hard cases" in the data for which annotated training data may be scarce. Our Method is evaluated on glands and nuclei datasets. We show that under both the inductive and transductive settings, our SSL Method consistently boosts the performance of common segmentation models and attains state-of-the-art results.
-
BIBM - Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation
2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020Co-Authors: Hongxiao Wang, Hao Zheng, Jianxu Chen, Lin Yang, Yizhe Zhang, Danny Z. ChenAbstract:Automatic histopathology image segmentation is crucial to disease analysis. Limited available labeled data hinders the generalizability of trained models under the fully supervised setting. Semi-supervised learning (SSL) based on Generative Methods has been proven to be effective in utilizing diverse image characteristics. However, it has not been well explored what kinds of generated images would be more useful for model training and how to use such images. In this paper, we propose a new data guided Generative Method for histopathology image segmentation by leveraging the unlabeled data distributions. First, we design an image generation module. Image content and style are disentangled and embedded in a clustering-friendly space to utilize their distributions. New images are synthesized by sampling and cross-combining contents and styles. Second, we devise an effective data selection policy for judiciously sampling the generated images: (1) to make the generated training set better cover the dataset, the clusters that are underrepresented in the original training set are covered more; (2) to make the training process more effective, we identify and oversample the images of “hard cases” in the data for which annotated training data may be scarce. Our Method is evaluated on glands and nuclei datasets. We show that under both the inductive and transductive settings, our SSL Method consistently boosts the performance of common segmentation models and attains state-of-the-art results.
Yizhou Wang - One of the best experts on this subject based on the ideXlab platform.
-
a Generative Method for textured motion analysis and synthesis
European Conference on Computer Vision, 2002Co-Authors: Yizhou Wang, Song-chun ZhuAbstract:Natural scenes contain rich stochastic motion patterns which are characterized by the movement of a large number of small elements, such as falling snow, raining, flying birds, firework and waterfall. In this paper, we call these motion patterns textured motion and present a Generative Method that combines statistical models and algorithms from both texture and motion analysis. The Generative Method includes the following three aspects. 1). Photometrically, an image is represented as a superposition of linear bases in atomic decomposition using an overcomplete dictionary, such as Gabor or Laplacian. Such base representation is known to be generic for natural images, and it is low dimensional as the number of bases is often 100 times smaller than the number of pixels. 2). Geometrically, each moving element (called moveton), such as the individual snowflake and bird, is represented by a deformable template which is a group of several spatially adjacent bases. Such templates are learned through clustering. 3). Dynamically, the movetons are tracked through the image sequence by a stochastic algorithm maximizing a posterior probability. A classic second order Markov chain model is adopted for the motion dynamics. The sources and sinks of the movetons are modeled by birth and death maps. We adopt an EM-like stochastic gradient algorithm for inference of the hidden variables: bases, movetons, birth/death maps, parameters of the dynamics. The learned models are also verified through synthesizing random textured motion sequences which bear similar visual appearance with the observed sequences.
-
ECCV (1) - A Generative Method for Textured Motion: Analysis and Synthesis
Computer Vision — ECCV 2002, 2002Co-Authors: Yizhou Wang, Song-chun ZhuAbstract:Natural scenes contain rich stochastic motion patterns which are characterized by the movement of a large number of small elements, such as falling snow, raining, flying birds, firework and waterfall. In this paper, we call these motion patterns textured motion and present a Generative Method that combines statistical models and algorithms from both texture and motion analysis. The Generative Method includes the following three aspects. 1). Photometrically, an image is represented as a superposition of linear bases in atomic decomposition using an overcomplete dictionary, such as Gabor or Laplacian. Such base representation is known to be generic for natural images, and it is low dimensional as the number of bases is often 100 times smaller than the number of pixels. 2). Geometrically, each moving element (called moveton), such as the individual snowflake and bird, is represented by a deformable template which is a group of several spatially adjacent bases. Such templates are learned through clustering. 3). Dynamically, the movetons are tracked through the image sequence by a stochastic algorithm maximizing a posterior probability. A classic second order Markov chain model is adopted for the motion dynamics. The sources and sinks of the movetons are modeled by birth and death maps. We adopt an EM-like stochastic gradient algorithm for inference of the hidden variables: bases, movetons, birth/death maps, parameters of the dynamics. The learned models are also verified through synthesizing random textured motion sequences which bear similar visual appearance with the observed sequences.
-
A Generative Method for Textured Motion: Analysis and Synthesis
2002Co-Authors: Yizhou Wang, Song-chun ZhuAbstract:Natural scenes contain rich stochastic motion patterns which are characterized by the movement of a large number of small elements, such as falling snow, raining, flying birds, firework and waterfall. In this paper, we call these motion patterns textured motion and present a Generative Method that combines statistical models and algorithms from both texture and motion analysis. The Generative Method includes the following aspects. !). Photometrically, an image is represented as a superposition of linear bases in atomic decomposition using an over-comlete dictionary, such as Gabor or Laplacian. Such base representation is known to be generic for natural images, and it is low dimensional as the number of bases is often 100 times smaller than the number of pixels. 2). Geometricall, each moving element (called moveton), such as the individual snowflake and bird, is represented by a deformable template which is a group of several spatially adjacent bases. Such templates are learned through clustering. 3). Dynamically, the movetons are tracked through the image sequence by a stochastic algorithm maximizing a posterior probability. A classic second order Markov chain model is adopted for the motion of dynamics. The sources and sinks of the movetons are modeled by birth and death maps. We adopt an EM-like stochastic gradient algorithm for inference of the hidden variables: bases, movetons, birth/death maps, parameters of the dynamics. The learned models are also verified through synthesizing random textured motion sequences which bear similar visual appearances with the ovserved sequences.
S M M Martens - One of the best experts on this subject based on the ideXlab platform.
-
a Generative model approach for decoding in the visual event related potential based brain computer interface speller
Journal of Neural Engineering, 2010Co-Authors: S M M Martens, J M LeivaAbstract:There is a strong tendency towards discriminative approaches in brain–computer interface (BCI) research. We argue that Generative model-based approaches are worth pursuing and propose a simple Generative model for the visual ERP-based BCI speller which incorporates prior knowledge about the brain signals. We show that the proposed Generative Method needs less training data to reach a given letter prediction performance than the state of the art discriminative approaches.
-
A Generative model approach for decoding in the visual event-related potential-based brain–computer interface speller
Journal of neural engineering, 2010Co-Authors: S M M Martens, J M LeivaAbstract:There is a strong tendency towards discriminative approaches in brain–computer interface (BCI) research. We argue that Generative model-based approaches are worth pursuing and propose a simple Generative model for the visual ERP-based BCI speller which incorporates prior knowledge about the brain signals. We show that the proposed Generative Method needs less training data to reach a given letter prediction performance than the state of the art discriminative approaches.
-
MLSP Competition, 2010: Description of first place Method
2010 IEEE International Workshop on Machine Learning for Signal Processing, 2010Co-Authors: Jose M. Leiva, S M M MartensAbstract:Our winning approach to the 2010 MLSP Competition is based on a Generative Method for P300-based BCI decoding, successfully applied to visual spellers. Here, Generative has a double meaning. On the one hand, we work with a probability density model of the data given the target/non target labeling, as opposed to discriminative (e.g. SVM-based) Methods. On the other hand, the natural consequence of this approach is a decoding based on comparing the observation to templates generated from the data.