Search

Your search keyword '"Chao, Wei-Lun"' showing total 30 results
Start Over Author "Chao, Wei-Lun" Publisher ieee
30 results on '"Chao, Wei-Lun"'

7. One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones

Author

Song, Chan Hee, Kil, Jihyung, Pan, Tai-Yu, Sadler, Brian M., Chao, Wei-Lun, and Su, Yu

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Robotics, Computer Science - Computation and Language, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Computation and Language (cs.CL), Robotics (cs.RO), Machine Learning (cs.LG)
Abstract

We study the problem of developing autonomous agents that can follow human instructions to infer and perform a sequence of actions to complete the underlying task. Significant progress has been made in recent years, especially for tasks with short horizons. However, when it comes to long-horizon tasks with extended sequences of actions, an agent can easily ignore some instructions or get stuck in the middle of the long instructions and eventually fail the task. To address this challenge, we propose a model-agnostic milestone-based task tracker (M-TRACK) to guide the agent and monitor its progress. Specifically, we propose a milestone builder that tags the instructions with navigation and interaction milestones which the agent needs to complete step by step, and a milestone checker that systemically checks the agent's progress in its current milestone and determines when to proceed to the next. On the challenging ALFRED dataset, our M-TRACK leads to a notable 33% and 52% relative improvement in unseen success rate over two competitive base models., Comment: 10 pages, 5 figures. Accepted to CVPR 2022

Published
2022

8. Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions

Author

Diaz-Ruiz, Carlos A., primary, Xia, Youya, additional, You, Yurong, additional, Nino, Jose, additional, Chen, Junan, additional, Monica, Josephine, additional, Chen, Xiangyu, additional, Luo, Katie, additional, Wang, Yan, additional, Emond, Marc, additional, Chao, Wei-Lun, additional, Hariharan, Bharath, additional, Weinberger, Kilian Q., additional, and Campbell, Mark, additional

Published
2022
Full Text
View/download PDF

12. Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation

Author

Yang, Luyu, Wang, Yan, Gao, Mingfei, Shrivastava, Abhinav, Weinberger, Kilian Q., Chao, Wei-Lun, and Lim, Ser-Nam

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Machine Learning (cs.LG)
Abstract

Semi-supervised domain adaptation (SSDA) aims to adapt models trained from a labeled source domain to a different but related target domain, from which unlabeled data and a small set of labeled data are provided. Current methods that treat source and target supervision without distinction overlook their inherent discrepancy, resulting in a source-dominated model that has not effectively used the target supervision. In this paper, we argue that the labeled target data needs to be distinguished for effective SSDA, and propose to explicitly decompose the SSDA task into two sub-tasks: a semi-supervised learning (SSL) task in the target domain and an unsupervised domain adaptation (UDA) task across domains. By doing so, the two sub-tasks can better leverage the corresponding supervision and thus yield very different classifiers. To integrate the strengths of the two classifiers, we apply the well-established co-training framework, in which the two classifiers exchange their high confident predictions to iteratively "teach each other" so that both classifiers can excel in the target domain. We call our approach Deep Co-training with Task decomposition (DeCoTa). DeCoTa requires no adversarial training and is easy to implement. Moreover, DeCoTa is well-founded on the theoretical condition of when co-training would succeed. As a result, DeCoTa achieves state-of-the-art results on several SSDA datasets, outperforming the prior art by a notable 4% margin on DomainNet. Code is available at https://github.com/LoyoYang/DeCoTa, accepted to ICCV 2021

Published
2021

15. Two-Stage Mesh Deep Learning for Automated Tooth Segmentation and Landmark Localization on 3D Intraoral Scans.

Author

Wu, Tai-Hsien, Lian, Chunfeng, Lee, Sanghee, Pastewait, Matthew, Piers, Christian, Liu, Jie, Wang, Fan, Wang, Li, Chiu, Chiung-Ying, Wang, Wenchi, Jackson, Christina, Chao, Wei-Lun, Shen, Dinggang, and Ko, Ching-Chang

Subjects
DEEP learning, TEETH, CORRECTIVE orthodontics, ORTHODONTISTS
Abstract

Accurately segmenting teeth and identifying the corresponding anatomical landmarks on dental mesh models are essential in computer-aided orthodontic treatment. Manually performing these two tasks is time-consuming, tedious, and, more importantly, highly dependent on orthodontists’ experiences due to the abnormality and large-scale variance of patients’ teeth. Some machine learning-based methods have been designed and applied in the orthodontic field to automatically segment dental meshes (e.g., intraoral scans). In contrast, the number of studies on tooth landmark localization is still limited. This paper proposes a two-stage framework based on mesh deep learning (called TS-MDL) for joint tooth labeling and landmark identification on raw intraoral scans. Our TS-MDL first adopts an end-to-end iMeshSegNet method (i.e., a variant of the existing MeshSegNet with both improved accuracy and efficiency) to label each tooth on the downsampled scan. Guided by the segmentation outputs, our TS-MDL further selects each tooth’s region of interest (ROI) on the original mesh to construct a light-weight variant of the pioneering PointNet (i.e., PointNet-Reg) for regressing the corresponding landmark heatmaps. Our TS-MDL was evaluated on a real-clinical dataset, showing promising segmentation and localization performance. Specifically, iMeshSegNet in the first stage of TS-MDL reached an averaged Dice similarity coefficient (DSC) at ${0.964}\pm {0.054}$ , significantly outperforming the original MeshSegNet. In the second stage, PointNet-Reg achieved a mean absolute error (MAE) of ${0}.{597}\pm {0}.{761} \, mm$ in distances between the prediction and ground truth for 66 landmarks, which is superior compared with other networks for landmark detection. All these results suggest the potential usage of our TS-MDL in orthodontics. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results