检索结果-内蒙古大学图书馆

International Conference on Electronic Engineering and Informatics (EEI)

作者： Jing Pang Ye Su Yiyuan Xie College of Electronic and Information Engineering Southwest University Chongqing People's Republic of China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing People's Republic of China Key Laboratory of Networks and Cloud Computing Security of Universities in Chongqing Chongqing People's Republic of China

ISBN: (数字)9798350353594

ISBN: (纸本)9798350353600

Integrated photonic neural networks (IPNNs), with their ability to process large-scale data and parallelize multiple computational tasks, have shown impressive promise for applications in the field of artificial intelligence. However, due to some hard-to-ignore non-ideal characteristics of the underlying silicon photonic MZI devices constituting the IPNN, these non-ideal characteristics can cause the input signal to be affected by crosstalk noise and optical loss during transmission, thus affecting the training and inference accuracy of the IPNN. In order to solve these problems, this paper establishes an analytical model of IPNN affected by crosstalk noise and loss during the training process, covering component level, layer level and system level. Simulations using this model show that the inference accuracy of IPNN decreases by about 65% when the crosstalk noise in the training phase of IPNN reaches -20 dB, while the inference accuracy of IPNN decreases by about 55% when the optical loss reaches -0.5 dB.

关键词： Training Optical losses Optical interferometry Accuracy Neural networks Crosstalk Optical computing Optical crosstalk Optical noise Optical devices

来源：评论

学校读者我要写书评

暂无评论

Rich-text document styling restoration via reinforcement learning

引用

Frontiers of Computer Science 2021年第4期15卷 93-103页

作者： Hongwei LI Yingpeng HU Yixuan CAO Ganbin ZHOU Ping LUO Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Search Product Center WeChat Search Application DepartmentTencentBeijing 100080China

Richly formatted documents,such as financial disclosures,scientific articles,government regulations,widely exist on ***,since most of these documents are only for public reading,the styling information inside them is usually missing,making them improper or even burdensome to be displayed and edited in different formats and *** this study we formulate the task of document styling restoration as an optimization problem,which aims to identify the styling settings on the document elements,e.g.,lines,table cells,text,so that rendering with the output styling settings results in a document,where each element inside it holds the(closely)exact position with the one in the original *** that each styling setting is a decision,this problem can be transformed as a multi-step decision-making task over all the document elements,and then be solved by reinforcement ***,Monte-Carlo Tree Search(MCTS)is leveraged to explore the different styling settings,and the policy function is learnt under the supervision of the delayed *** a case study,we restore the styling information inside tables,where structural and functional data in the documents are usually *** shows that,our best reinforcement method successfully restores the stylings in 87.65%of the tables,with 25.75%absolute improvement over the *** also discuss the tradeoff between the inference time and restoration success rate,and argue that although the reinforcement methods cannot be used in real-time scenarios,it is suitable for the offline tasks with high-quality ***,this model has been applied in a PDF parser to support cross-format display.

关键词： styling restoration monte-carlo tree search reinforcement learning richly formatted documents tables

来源：评论

学校读者我要写书评

暂无评论

Layout-based Causal Inference for Object Navigation

Layout-based Causal Inference for Object Navigation

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sixian Zhang Xinhang Song Weijie Li Yubing Bai Xinyao Yu Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing

Previous works for ObjectNav task attempt to learn the association (e.g. relation graph) between the visual inputs and the goal during training. Such association contains the prior knowledge of navigating in training environments, which is denoted as the experience. The experience performs a positive effect on helping the agent infer the likely location of the goal when the layout gap between the unseen environments of the test and the prior knowledge obtained in training is minor. However, when the layout gap is significant, the experience exerts a negative effect on navigation. Motivated by keeping the positive effect and removing the negative effect of the experience, we propose the layout-based soft Total Direct Effect (L-sTDE) framework based on the causal inference to adjust the prediction of the navigation policy. In particular, we propose to calculate the layout gap which is defined as the KL divergence between the posterior and the prior distribution of the object layout. Then the sTDE is proposed to appropriately control the effect of the experience based on the layout gap. Experimental results on AI2THOR, RoboTHOR, and Habitat demonstrate the effectiveness of our method. The code is available at https://***/sx-zhang/***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DragEntity:Trajectory Guided Video Generation using Entity and Positional Relationships

arXiv

引用

arXiv 2024年

作者： Wan, Zhang Tang, Sheng Wei, Jiawei Zhang, Ruize Cao, Juan Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Zhengzhou University Zhengzhou China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

In recent years, diffusion models have achieved tremendous success in the field of video generation, with controllable video generation receiving significant attention. However, existing control methods still face two limitations: Firstly, control conditions (such as depth maps, 3D Mesh) are difficult for ordinary users to obtain directly. Secondly, it’s challenging to drive multiple objects through complex motions with multiple trajectories simultaneously. In this paper, we introduce DragEntity, a video generation model that utilizes entity representation for controlling the motion of multiple objects. Compared to previous methods, DragEntity offers two main advantages: 1) Our method is more user-friendly for interaction because it allows users to drag entities within the image rather than individual pixels. 2) We use entity representation to represent any object in the image, and multiple objects can maintain relative spatial relationships. Therefore, we allow multiple trajectories to control multiple objects in the image with different levels of complexity simultaneously. Our experiments validate the effectiveness of DragEntity, demonstrating its excellent performance in fine-grained control in video generation. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bi-Level Meta-Learning for Few-Shot Domain Generalization

Bi-Level Meta-Learning for Few-Shot Domain Generalization

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiaorong Qin Xinhang Song Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing

The goal of few-shot learning is to learn the generalization from seen to unseen data with only a few samples. Most previous few-shot learning methods focus on learning the generalization within particular domains. However, the more practical scenarios may also require the generalization ability across domains. In this paper, we study the problem of few-shot domain generalization (FSDG), which is a more challenging variant of few-shot classification. FSDG requires additional generalization with larger gap from seen domains to unseen domains. We address FSDG problem by meta-learning two levels of meta-knowledge, where the lower-level meta-knowledge is domain-specific embedding spaces as subspaces of a base space for intra-domain generalization, and the upper-level meta-knowledge is the base space and a prior subspace over domain-specific spaces for inter-domain generalization. We formulate the two levels of meta-knowledge learning problem with bi-level optimization, and further develop an optimization algorithm without higher-order derivative information to solve it. We demonstrate our method is significantly superior to the previous works by evaluating it on the widely used benchmark Meta-Dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fact-Preserved Personalized News Headline Generation

Fact-Preserved Personalized News Headline Generation

引用

IEEE International Conference on Data Mining (ICDM)

作者： Zhao Yang Junhong Lian Xiang Ao Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Institute of Intelligent Computing Technology Suzhou CAS

Personalized news headline generation, aiming at generating user-specific headlines based on readers’ preferences, burgeons a recent flourishing research direction. Existing studies generally inject a user interest embedding into an encoder-decoder headline generator to make the output personalized, while the factual consistency of headlines is inadequate to be verified. In this paper, we propose a framework Fact-Preserved Personalized News Headline Generation (short for FPG), to prompt a tradeoff between personalization and consistency. In FPG, the similarity between the candidate news to be exposed and the historical clicked news is used to give different levels of attention to key facts in the candidate news, and the similarity scores help to learn a fact-aware global user embedding. Besides, an additional training procedure based on contrastive learning is devised to further enhance the factual consistency of generated headlines. Extensive experiments conducted on a real-world benchmark PENS 1 validate the superiority of FPG, especially on the tradeoff between personalization and factual consistency. 1 https://***/***

关键词：

来源：评论

学校读者我要写书评

暂无评论

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning

arXiv

引用

arXiv 2022年

作者： Wang, Rui Chen, Dongdong Wu, Zuxuan Chen, Yinpeng Dai, Xiyang Liu, Mengchen Yuan, Lu Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan Univeristy China Microsoft Cloud + AI

Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like raw pixel RGB values. In this paper, we propose masked video distillation (MVD), a simple yet effective two-stage masked feature modeling framework for video representation learning: firstly we pretrain an image (or video) model by recovering low-level features of masked patches, then we use the resulting features as targets for masked feature modeling. For the choice of teacher models, we observe that students taught by video teachers perform better on temporally-heavy video tasks, while image teachers transfer stronger spatial representations for spatially-heavy video tasks. Visualization analysis also indicates different teachers produce different learned patterns for students. Motivated by this observation, to leverage the advantage of different teachers, we design a spatial-temporal co-teaching method for MVD. Specifically, we distill student models from both video teachers and image teachers by masked feature modeling. Extensive experimental results demonstrate that video transformers pretrained with spatial-temporal co-teaching outperform models distilled with a single teacher on a multitude of video datasets. Our MVD with vanilla ViT achieves state-of-the-art performance compared with previous supervised or self-supervised methods on several challenging video downstream tasks. For example, with the ViT-Large model, our MVD achieves 86.4% and 76.7% Top-1 accuracy on Kinetics-400 and Something-Something-v2, outperforming VideoMAE by 1.2% and 2.4% respectively. When a larger ViT-Huge model is adopted, MVD achieves the state-of-the-art performance with 77.3% Top-1 accuracy on Something- Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Non-autoregressive machine translation with probabilistic context-free grammar 23

Non-autoregressive machine translation with probabilistic co...

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Shangtong Gui Chenze Shao Zhengrui Ma Xishan Zhang Yunji Chen Yang Feng State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and Cambricon Technologies State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation. Code is publicly available at https://***/ictnlp/PCFG-NAT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Semantic Overlay on Blockchain for Supporting Traceability in Cross-border Logistics

A Semantic Overlay on Blockchain for Supporting Traceability...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Xiaoping Sun Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9781665492270

ISBN: (纸本)9781665492287

Traceability is important for maintaining quality of logistics transactions and improving logistics efficiency. Implementing traceability for cross-border logistics is facing challenges when it lacks global centralized logistics information management services. Blockchain techniques enable a decentralized cross-border logistics management by publishing logistics transaction on blockchain transactions to support privacy protection and traceability. Logistics transactions involves complex interactions among participants. How to publish those interactions on a blockchain platform is a challenge. We propose a semantic overlay model that publishes a logistics transaction as a semantic link on a blockchain platform for supporting traceability. A semantic link schema model is designed and published on the blockchain platform to validate semantics links for ensuring the correctness of logistics transaction execution. The proposed semantic overlay on blockchain supports further extension of semantic computing in decentralized applications.

关键词： Privacy Overlay networks Publishing Law Computational modeling Semantics Smart contracts

来源：评论

学校读者我要写书评

暂无评论

Harnessing Hierarchical label Distribution Variations in Test Agnostic Long-tail Recognition 41

Harnessing Hierarchical Label Distribution Variations in Tes...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Zhiyong Xu, Qianqian Wang, Zitai Li, Sicong Han, Boyu Bao, Shilong Cao, Xiaochun Huang, Qingming School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test label distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, DirMixE, which assigns experts to different Dirichlet meta-distributions of the label distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of DirMixE. The code is available at https://***/scongl/DirMixE. Copyright 2024 by the author(s)

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：