CASIA OpenIR

浏览/检索结果: 共111条,第1-10条 帮助

限定条件                    
已选(0)清除 条数/页:   排序方式:
Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentation 会议论文
, Virtual Venue, February 22 – March 1, 2022
作者:  Yaoru Luo;  Guole Liu;  Yuanhao Guo;  Ge Yang
Adobe PDF(7981Kb)  |  收藏  |  浏览/下载:8/3  |  提交时间:2024/06/11
Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation 会议论文
, London, UK, May 29 - June 2, 2023
作者:  Lu Zhang;  Siqi Zhang;  Xu Yang;  Hong Qiao;  Zhiyong Li
Adobe PDF(963Kb)  |  收藏  |  浏览/下载:14/4  |  提交时间:2024/06/06
Driving Control with Deep and Reinforcement Learning in The Open Racing Car Simulator 会议论文
, Siem Reap, Cambodia, 2018, 12, 13-16
作者:  Yuanheng Zhu;  Dongbin Zhao
Adobe PDF(697Kb)  |  收藏  |  浏览/下载:8/3  |  提交时间:2024/06/05
ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning 会议论文
, New Orleans, USA, 2023 年 12 月 10 日 – 2023 年 12 月 16 日
作者:  Mingyu Xu;  Zheng Lian;  Lei Feng;  Bin Liu;  Jianhua Tao
Adobe PDF(861Kb)  |  收藏  |  浏览/下载:18/6  |  提交时间:2024/05/31
Enhancing Fine-Tuning Performance of Text-to-Image Diffusion Models for Few-Shot Image Generation Through Contrastive Learning 会议论文
, 北京, 2024-8
作者:  Zhu, Yanlin;  Yang,Peipei
Adobe PDF(15243Kb)  |  收藏  |  浏览/下载:10/2  |  提交时间:2024/05/31
Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control 会议论文
Advances in Neural Information Processing Systems, New Orleans, USA, 2023-12-10
作者:  Chao Li;  Chen Gong;  Qiang He;  Xinwen Hou
Adobe PDF(1457Kb)  |  收藏  |  浏览/下载:16/4  |  提交时间:2024/05/30
D2AH-PPO: Playing ViZDoom With Object-Aware Hierarchical Reinforcement Learning 会议论文
, 中国重庆, 2024.5.7-5.9
作者:  Niu LY(钮龙宇);  Wan J(万军)
Adobe PDF(1645Kb)  |  收藏  |  浏览/下载:21/3  |  提交时间:2024/05/28
深度强化学习  表征学习  分层学习  
Explainable Reinforcement Learning via a Causal World Model 会议论文
Proceedings of the 32nd International Joint Conference on Artificial Intelligence, 中国澳门, 2023-08-22
作者:  Yu ZY(余忠蔚);  Ruan JQ(阮景晴);  Xing DP(邢登鹏)
Adobe PDF(850Kb)  |  收藏  |  浏览/下载:14/6  |  提交时间:2024/05/28
强化学习  可解释人工智能  因果推理  
Learning Causal Dynamics Models in Object-Oriented Environments 会议论文
Proceedings of the 41st International Conference on Machine Learning, 奥地利, 维也纳, 2024-07-21
作者:  Yu ZY(余忠蔚);  Ruan JQ(阮景晴);  Xing DP(邢登鹏)
Adobe PDF(2176Kb)  |  收藏  |  浏览/下载:12/4  |  提交时间:2024/05/28
强化学习  因果模型  
Efficient Hierarchical Reinforcement Learning via Mutual Information Constrained Subgoal Discovery 会议论文
, 长沙, 2023-11
作者:  Kaishen Wang;  Jingqing Ruan;  Qingyang Zhang;  Dengpeng Xing
Adobe PDF(2044Kb)  |  收藏  |  浏览/下载:11/6  |  提交时间:2024/05/28