The Experts below are selected from a list of 30 Experts worldwide ranked by ideXlab platform
M. S. Ryoo - One of the best experts on this subject based on the ideXlab platform.
-
Model-Based Robot Imitation with Future Image Similarity
International Journal of Computer Vision, 2020Co-Authors: Aj Piergiovanni, M. S. RyooAbstract:We present a visual imitation learning framework that enables learning of robot action policies solely based on expert samples without any robot trials. Robot exploration and on-policy trials in a real-world environment could often be expensive/dangerous. We present a new approach to address this problem by learning a future scene prediction model solely from a collection of expert trajectories consisting of Unlabeled Example videos and actions, and by enabling action selection using future image similarity . In this approach, the robot learns to visually imagine the consequences of taking an action, and obtains the policy by evaluating how similar the predicted future image is to an expert sample. We develop an action-conditioned convolutional autoencoder, and present how we take advantage of future images for zero-online-trial imitation learning. We conduct experiments in simulated and real-life environments using a ground mobility robot with and without obstacles in reaching target objects. We explicitly compare our models to multiple baseline methods requiring only offline samples. The results confirm that our proposed methods perform superior to previous methods, including 1.5 $$\times $$ × and 2.5 $$\times $$ × higher success rate in two different tasks than behavioral cloning.
Aj Piergiovanni - One of the best experts on this subject based on the ideXlab platform.
-
Model-Based Robot Imitation with Future Image Similarity
International Journal of Computer Vision, 2020Co-Authors: Aj Piergiovanni, M. S. RyooAbstract:We present a visual imitation learning framework that enables learning of robot action policies solely based on expert samples without any robot trials. Robot exploration and on-policy trials in a real-world environment could often be expensive/dangerous. We present a new approach to address this problem by learning a future scene prediction model solely from a collection of expert trajectories consisting of Unlabeled Example videos and actions, and by enabling action selection using future image similarity . In this approach, the robot learns to visually imagine the consequences of taking an action, and obtains the policy by evaluating how similar the predicted future image is to an expert sample. We develop an action-conditioned convolutional autoencoder, and present how we take advantage of future images for zero-online-trial imitation learning. We conduct experiments in simulated and real-life environments using a ground mobility robot with and without obstacles in reaching target objects. We explicitly compare our models to multiple baseline methods requiring only offline samples. The results confirm that our proposed methods perform superior to previous methods, including 1.5 $$\times $$ × and 2.5 $$\times $$ × higher success rate in two different tasks than behavioral cloning.
-
Model-based Behavioral Cloning with Future Image Similarity Learning
2019Co-Authors: Wu Alan, Aj Piergiovanni, Ryoo, Michael S.Abstract:We present a visual imitation learning framework that enables learning of robot action policies solely based on expert samples without any robot trials. Robot exploration and on-policy trials in a real-world environment could often be expensive/dangerous. We present a new approach to address this problem by learning a future scene prediction model solely on a collection of expert trajectories consisting of Unlabeled Example videos and actions, and by enabling generalized action cloning using future image similarity. The robot learns to visually predict the consequences of taking an action, and obtains the policy by evaluating how similar the predicted future image is to an expert image. We develop a stochastic action-conditioned convolutional autoencoder, and present how we take advantage of future images for robot learning. We conduct experiments in simulated and real-life environments using a ground mobility robot with and without obstacles, and compare our models to multiple baseline methods
Benjamin K Tsou - One of the best experts on this subject based on the ideXlab platform.
-
a density based re ranking technique for active learning for data annotations
International Conference on the Computer Processing of Oriental Languages, 2009Co-Authors: Jingbo Zhu, Huizhen Wang, Benjamin K TsouAbstract:One of the popular techniques of active learning for data annotations is uncertainty sampling, however, which often presents problems when outliers are selected. To solve this problem, this paper proposes a density-based re-ranking technique, in which a density measure is adopted to determine whether an Unlabeled Example is an outlier. The motivation of this study is to prefer not only the most informative Example in terms of uncertainty measure, but also the most representative Example in terms of density measure. Experimental results of active learning for word sense disambiguation and text classification tasks using six real-world evaluation data sets show that our proposed density-based re-ranking technique can improve uncertainty sampling.
-
active learning with sampling by uncertainty and density for word sense disambiguation and text classification
International Conference on Computational Linguistics, 2008Co-Authors: Jingbo Zhu, Huizhen Wang, Tianshun Yao, Benjamin K TsouAbstract:This paper addresses two issues of active learning. Firstly, to solve a problem of uncertainty sampling that it often fails by selecting outliers, this paper presents a new selective sampling technique, sampling by uncertainty and density (SUD), in which a k-Nearest-Neighbor-based density measure is adopted to determine whether an Unlabeled Example is an outlier. Secondly, a technique of sampling by clustering (SBC) is applied to build a representative initial training data set for active learning. Finally, we implement a new algorithm of active learning with SUD and SBC techniques. The experimental results from three real-world data sets show that our method outperforms competing methods, particularly at the early stages of active learning.
Jingbo Zhu - One of the best experts on this subject based on the ideXlab platform.
-
a density based re ranking technique for active learning for data annotations
International Conference on the Computer Processing of Oriental Languages, 2009Co-Authors: Jingbo Zhu, Huizhen Wang, Benjamin K TsouAbstract:One of the popular techniques of active learning for data annotations is uncertainty sampling, however, which often presents problems when outliers are selected. To solve this problem, this paper proposes a density-based re-ranking technique, in which a density measure is adopted to determine whether an Unlabeled Example is an outlier. The motivation of this study is to prefer not only the most informative Example in terms of uncertainty measure, but also the most representative Example in terms of density measure. Experimental results of active learning for word sense disambiguation and text classification tasks using six real-world evaluation data sets show that our proposed density-based re-ranking technique can improve uncertainty sampling.
-
active learning with sampling by uncertainty and density for word sense disambiguation and text classification
International Conference on Computational Linguistics, 2008Co-Authors: Jingbo Zhu, Huizhen Wang, Tianshun Yao, Benjamin K TsouAbstract:This paper addresses two issues of active learning. Firstly, to solve a problem of uncertainty sampling that it often fails by selecting outliers, this paper presents a new selective sampling technique, sampling by uncertainty and density (SUD), in which a k-Nearest-Neighbor-based density measure is adopted to determine whether an Unlabeled Example is an outlier. Secondly, a technique of sampling by clustering (SBC) is applied to build a representative initial training data set for active learning. Finally, we implement a new algorithm of active learning with SUD and SBC techniques. The experimental results from three real-world data sets show that our method outperforms competing methods, particularly at the early stages of active learning.
Huizhen Wang - One of the best experts on this subject based on the ideXlab platform.
-
a density based re ranking technique for active learning for data annotations
International Conference on the Computer Processing of Oriental Languages, 2009Co-Authors: Jingbo Zhu, Huizhen Wang, Benjamin K TsouAbstract:One of the popular techniques of active learning for data annotations is uncertainty sampling, however, which often presents problems when outliers are selected. To solve this problem, this paper proposes a density-based re-ranking technique, in which a density measure is adopted to determine whether an Unlabeled Example is an outlier. The motivation of this study is to prefer not only the most informative Example in terms of uncertainty measure, but also the most representative Example in terms of density measure. Experimental results of active learning for word sense disambiguation and text classification tasks using six real-world evaluation data sets show that our proposed density-based re-ranking technique can improve uncertainty sampling.
-
active learning with sampling by uncertainty and density for word sense disambiguation and text classification
International Conference on Computational Linguistics, 2008Co-Authors: Jingbo Zhu, Huizhen Wang, Tianshun Yao, Benjamin K TsouAbstract:This paper addresses two issues of active learning. Firstly, to solve a problem of uncertainty sampling that it often fails by selecting outliers, this paper presents a new selective sampling technique, sampling by uncertainty and density (SUD), in which a k-Nearest-Neighbor-based density measure is adopted to determine whether an Unlabeled Example is an outlier. Secondly, a technique of sampling by clustering (SBC) is applied to build a representative initial training data set for active learning. Finally, we implement a new algorithm of active learning with SUD and SBC techniques. The experimental results from three real-world data sets show that our method outperforms competing methods, particularly at the early stages of active learning.