Science China Information Sciences最新文献_第8页

Continuous advantage learning for minimum-time trajectory planning of autonomous vehicles 自动驾驶汽车最小时间轨迹规划的持续优势学习

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-25 DOI: 10.1007/s11432-023-4059-6

Zhuo Li, Weiran Wu, Jialin Wang, Gang Wang, Jian Sun

引用次数: 0

Ensemble successor representations for task generalization in offline-to-online reinforcement learning 离线到在线强化学习中任务泛化的集合后继表征

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-25 DOI: 10.1007/s11432-023-4028-1

Changhong Wang, Xudong Yu, Chenjia Bai, Qiaosheng Zhang, Zhen Wang

{"title":"Ensemble successor representations for task generalization in offline-to-online reinforcement learning","authors":"Changhong Wang, Xudong Yu, Chenjia Bai, Qiaosheng Zhang, Zhen Wang","doi":"10.1007/s11432-023-4028-1","DOIUrl":"https://doi.org/10.1007/s11432-023-4028-1","url":null,"abstract":"In reinforcement learning (RL), training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration. Recently, offline RL provides a promising solution by giving an initialized offline policy, which can be refined through online interactions. However, existing approaches primarily perform offline and online learning in the same task, without considering the task generalization problem in offline-to-online adaptation. In real-world applications, it is common that we only have an offline dataset from a specific task while aiming for fast online-adaptation for several tasks. To address this problem, our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning. We demonstrate that the conventional paradigm using successor features cannot effectively utilize offline data and improve the performance for the new task by online fine-tuning. To mitigate this, we introduce a novel methodology that leverages offline data to acquire an ensemble of successor representations and subsequently constructs ensemble Q functions. This approach enables robust representation learning from datasets with different coverage and facilitates fast adaption of Q functions towards new tasks during the online fine-tuning phase. Extensive empirical evaluations provide compelling evidence showcasing the superior performance of our method in generalizing to diverse or even unseen tasks.","PeriodicalId":21618,"journal":{"name":"Science China Information Sciences","volume":"75 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141502710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An ensemble and cost-sensitive learning-based root cause diagnosis scheme for wireless networks with spatially imbalanced user data distribution 针对用户数据空间分布不平衡的无线网络的基于集合和成本敏感学习的根本原因诊断方案

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-25 DOI: 10.1007/s11432-023-4055-1

Qi Wang, Zhiwen Pan, Nan Liu

引用次数: 0

Towards imbalanced motion: part-decoupling network for video portrait segmentation 实现不平衡运动：用于视频肖像分割的部分解耦网络

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-25 DOI: 10.1007/s11432-023-4030-y

Tianshu Yu, Changqun Xia, Jia Li

{"title":"Towards imbalanced motion: part-decoupling network for video portrait segmentation","authors":"Tianshu Yu, Changqun Xia, Jia Li","doi":"10.1007/s11432-023-4030-y","DOIUrl":"https://doi.org/10.1007/s11432-023-4030-y","url":null,"abstract":"Video portrait segmentation (VPS), aiming at segmenting prominent foreground portraits from video frames, has received much attention in recent years. However, the simplicity of existing VPS datasets leads to a limitation on extensive research of the task. In this work, we propose a new intricate large-scale multi-scene video portrait segmentation dataset MVPS consisting of 101 video clips in 7 scenario categories, in which 10843 sampled frames are finely annotated at the pixel level. The dataset has diverse scenes and complicated background environments, which is the most complex dataset in VPS to our best knowledge. Through the observation of a large number of videos with portraits during dataset construction, we find that due to the joint structure of the human body, the motion of portraits is part-associated, which leads to the different parts being relatively independent in motion. That is, the motion of different parts of the portraits is imbalanced. Towards this imbalance, an intuitive and reasonable idea is that different motion states in portraits can be better exploited by decoupling the portraits into parts. To achieve this, we propose a part-decoupling network (PDNet) for VPS. Specifically, an inter-frame part-discriminated attention (IPDA) module is proposed which unsupervisedly segments portrait into parts and utilizes different attentiveness on discriminative features specified to each different part. In this way, appropriate attention can be imposed on portrait parts with imbalanced motion to extract part-discriminated correlations, so that the portraits can be segmented more accurately. Experimental results demonstrate that our method achieves leading performance with the comparison to state-of-the-art methods.","PeriodicalId":21618,"journal":{"name":"Science China Information Sciences","volume":"41 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141516007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rethinking attribute localization for zero-shot learning 反思零点学习的属性定位

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-25 DOI: 10.1007/s11432-023-4051-9

Shuhuang Chen, Shiming Chen, Guo-Sen Xie, Xiangbo Shu, Xinge You, Xuelong Li

{"title":"Rethinking attribute localization for zero-shot learning","authors":"Shuhuang Chen, Shiming Chen, Guo-Sen Xie, Xiangbo Shu, Xinge You, Xuelong Li","doi":"10.1007/s11432-023-4051-9","DOIUrl":"https://doi.org/10.1007/s11432-023-4051-9","url":null,"abstract":"Recent advancements in attribute localization have showcased its potential in discovering the intrinsic semantic knowledge for visual feature representations, thereby facilitating significant visual-semantic interactions essential for zero-shot learning (ZSL). However, the majority of existing attribute localization methods heavily rely on classification constraints, resulting in accurate localization of only a few attributes while neglecting the rest important attributes associated with other classes. This limitation hinders the discovery of the intrinsic semantic relationships between attributes and visual features across all classes. To address this problem, we propose a novel attribute localization refinement (ALR) module designed to enhance the model’s ability to accurately localize all attributes. Essentially, we enhance weak discriminant attributes by grouping them and introduce weighted attribute regression to standardize the mapping values of semantic attributes. This module can be flexibly combined with existing attribute localization methods. Our experiments show that when combined with the ALR module, the localization errors in existing methods are corrected, and state-of-the-art classification performance is achieved.","PeriodicalId":21618,"journal":{"name":"Science China Information Sciences","volume":"9 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141784755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive neural network control of a 2-DOF helicopter system considering input constraints and global prescribed performance 考虑输入约束和全局规定性能的 2-DOF 直升机系统的自适应神经网络控制

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-25 DOI: 10.1007/s11432-023-3949-3

Zhijia Zhao, Jiale Wu, Zhijie Liu, We He, C. L. Philip Chen

引用次数: 0

Shor’s algorithm does not factor large integers in the presence of noise 肖尔算法在有噪声的情况下不能对大整数进行因式分解

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-18 DOI: 10.1007/s11432-023-3961-3

Jin-Yi Cai

引用次数: 0

A unified intelligent control strategy synthesizing multi-constrained guidance and avoidance penetration 综合多约束制导和避让穿透的统一智能控制策略

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-14 DOI: 10.1007/s11432-022-4063-x

Sibo Zhao, Jianwen Zhu, Weimin Bao, Xiaoping Li

引用次数: 0

Highly sensitive flexible strain sensor based on the two-dimensional semiconductor tellurium with a negative gauge factor 基于负测量因子二维半导体碲的高灵敏柔性应变传感器

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-06-13 DOI: 10.1007/s11432-023-3938-y

Jiarui He, Yusong Qu, Shengyao Chen, Cong Wang, Lena Du, Xiaoshan Du, Yuanyuan Zheng, Guozhong Zhao, He Tian

{"title":"Highly sensitive flexible strain sensor based on the two-dimensional semiconductor tellurium with a negative gauge factor","authors":"Jiarui He, Yusong Qu, Shengyao Chen, Cong Wang, Lena Du, Xiaoshan Du, Yuanyuan Zheng, Guozhong Zhao, He Tian","doi":"10.1007/s11432-023-3938-y","DOIUrl":"https://doi.org/10.1007/s11432-023-3938-y","url":null,"abstract":"Research on flexible strain sensors has advanced rapidly in recent years, with particular attention being devoted to two-dimensional (2D) semiconductor materials owing to their exceptional mechanical and electrical properties that are conducive to sophisticated sensing performance. However, resistive strain sensors based on 2D semiconductor materials typically exhibit positive gauge factors (GF), while materials for strain sensors with a negative GF remain elusive. We have identified a trend of reduction in the band gap of the emerging 2D semiconductor material tellurium (Te) under strain in simulations reported in past research, and have observed a negative GF in the Te-based strain sensor. In this study, we combined Te with a flexible polyethylene terephthalate (PET) substrate to manufacture a flexible strain sensor with a significantly negative GF. The results of tests revealed that the Te-based strain sensor achieved an impressive maximum sensitivity of −139.7 within a small range of bending-induced strain (< 1%). Furthermore, it exhibited excellent linearity and good cyclic stability, and was successfully applied to monitor limb movements. The work here verifies the significant potential for the use of Te-based strain sensors in next-generation flexible electronics.","PeriodicalId":21618,"journal":{"name":"Science China Information Sciences","volume":"25 1","pages":""},"PeriodicalIF":8.8,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141502714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Constructions of optimal binary locally repairable codes via intersection subspaces 通过交集子空间构建最优二进制局部可修复代码

IF 8.8 2区计算机科学

Science China Information Sciences Pub Date : 2024-05-29 DOI: 10.1007/s11432-023-3863-y

Wenqin Zhang, Deng Tang, Chenhao Ying, Yuan Luo

引用次数: 0