Search

Your search keyword '"Wang, Chuanyun"' showing total 230 results
Start Over Author "Wang, Chuanyun" Publication Year Range Last 10 years
230 results on '"Wang, Chuanyun"'

13. Region based Ensemble Learning Network for Fine-grained Classification

Author

Li, Weikuang, Wang, Tian, Wang, Chuanyun, Shan, Guangcun, Zhang, Mengyi, and Snoussi, Hichem

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

As an important research topic in computer vision, fine-grained classification which aims to recognition subordinate-level categories has attracted significant attention. We propose a novel region based ensemble learning network for fine-grained classification. Our approach contains a detection module and a module for classification. The detection module is based on the faster R-CNN framework to locate the semantic regions of the object. The classification module using an ensemble learning method, which trains a set of sub-classifiers for different semantic regions and combines them together to get a stronger classifier. In the evaluation, we implement experiments on the CUB-2011 dataset and the result of experiments proves our method s efficient for fine-grained classification. We also extend our approach to remote scene recognition and evaluate it on the NWPU-RESISC45 dataset., Comment: 6 pages, 3 figures, 2018 Chinese Automation Congress (CAC)

Published
2019
Full Text
View/download PDF

35. Multiple deformation mechanisms induce high work hardening in Ti–5Al–7.5 V alloy via transformed β matrix.

Author

Xie, Sisi, Wu, Zhihong, Chen, Nana, Zhu, Mingxiang, Yang, Hao, Zhang, Zilong, Wang, Chuanyun, Li, Jinshan, and Kou, Hongchao

Subjects
STRAIN hardening, MARTENSITIC transformations, DEFORMATIONS (Mechanics), ALLOYS, TITANIUM alloys
Abstract

In this work, different transformed β matrix was obtained in Ti–5Al–7.5 V alloy. The alloy with equiaxed αp phase and transformed β matrix containing α′ martensite and β phase exhibits good combination of strength and plasticity, as well as a high work hardening rate. A concurrent operation of stress-induced α″ martensitic transformation, deformation twinning and dislocation slips was observed governing the deformation process of this alloy. The alloy with equiaxed αp phase and transformed β matrix containing secondary αs plates and retained β phase shows a high strength and plasticity but low work hardening rate, which is caused by dislocation slips. Highlights The quenched Ti–5Al–7.5 V alloy exhibits a high work hardening rate, approximately 5500 MPa. The dependence of work hardening rate of Ti–5Al–7.5 V alloy on transformed β matrix is revealed. Concurrent operations of stress-induced α″ martensitic transformation, deformation twinning and dislocation slips govern deformation of the studied alloy. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

43. Target-Driven Visual Navigation by Using Causal Intervention

Author

Zhao, Xinzhou, Wang, Tian, Li, Yanjing, Zhang, Baochang, Liu, Kexin, Liu, Deyuan, Wang, Chuanyun, and Snoussi, Hichem

Abstract

Target-driven visual navigation presents great potentials in scientific and industrial fields. It takes the target and environment observations as input. However, during training, we found that the agent sometimes got stuck in specific locations. Based on the analysis on visual information from a novel causal perspective, one of the most critical hurdles is the neglect of confounders in environments, which often leads to spurious correlations. Mitigating the confounding effect helps to discover the real causality and therefore are taken into consideration in other fields such as object detection. In this article, we propose Causal Intervention Visual Navigation (CIVN), based on deep reinforcement learning (DRL) and causal intervention. We realize causal intervention using front-door adjustment as most confounders are hard to model explicitly. Specifically, CIVN is implemented by Causal Attention, which is a reasonable approximation of causal intervention for visual navigation. Causal attention provides high-quality representation, which is leveraged by DRL and reduces the number of “stuck”. It is worth mentioned that causal intervention is for the first time applied by us in solving the confounding effect in target-driven visual navigation. Extensive experiments on AI2-THOR demonstrate that CIVN achieves better performance than prior arts. Specifically, the generalization for unknown targets and scenes is improved by a large margin, which is a basic research topic in visual navigation. Moreover, to obtain better generalization, we propose a novel experiment utilizing pre-trained models firstly.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results