检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wang, Xiaohua Wang, Zhenghua Gao, Xuan Zhang, Feiran Wu, Yixin Xu, Zhibo Shi, Tianyuan Wang, Zhengyuan Li, Shizheng Qian, Qi Yin, Ruicheng Lv, Changze Zheng, Xiaoqing Huang, Xuanjing School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (纸本)9798891761643

Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While many RAG approaches have been proposed to enhance large language models through query-dependent retrievals, these approaches still suffer from their complex implementation and prolonged response times. Typically, a RAG workflow involves multiple processing steps, each of which can be executed in various ways. Here, we investigate existing RAG approaches and their potential combinations to identify optimal RAG practices. Through extensive experiments, we suggest several strategies for deploying RAG that balance both performance and efficiency. Moreover, we demonstrate that multimodal retrieval techniques can significantly enhance question-answering capabilities about visual inputs and accelerate the generation of multimodal content using a "retrieval as generation" strategy. Code and resources are available at https://***/FudanDNN-NLP/RAG. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

MVSFORMER++: REVEALING THE DEVIL IN TRANSFORMER'S DETAILS FOR MULTI-VIEW STEREO 12

MVSFORMER++: REVEALING THE DEVIL IN TRANSFORMER'S DETAILS FO...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Cao, Chenjie Ren, Xinlin Fu, Yanwei School of Data Science Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China

Recent advancements in learning-based Multi-View Stereo (MVS) methods have prominently featured transformer-based models with attention mechanisms. However, existing approaches have not thoroughly investigated the profound influence of transformers on different MVS modules, resulting in limited depth estimation capabilities. In this paper, we introduce MVSFormer++, a method that prudently maximizes the inherent characteristics of attention to enhance various components of the MVS pipeline. Formally, our approach involves infusing cross-view information into the pre-trained DINOv2 model to facilitate MVS learning. Furthermore, we employ different attention mechanisms for the feature encoder and cost volume regularization, focusing on feature and spatial aggregations respectively. Additionally, we uncover that some design details would substantially impact the performance of transformer modules in MVS, including normalized 3D positional encoding, adaptive attention scaling, and the position of layer normalization. Comprehensive experiments on DTU, Tanks-and-Temples, BlendedMVS, and ETH3D validate the effectiveness of the proposed method. Notably, MVSFormer++ achieves state-of-the-art performance on the challenging DTU and Tanks-and-Temples benchmarks. Codes and models are available at https://***/maybeLx/MVSFormerPlusPlus. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Learning Cross-Spectral Prior for Image Super-Resolution 24

Learning Cross-Spectral Prior for Image Super-Resolution

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ma, Chenxi Tan, Weimin Zhou, Shili Yan, Bo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9798400706868

With the rising interest in multi-camera cross-spectral systems, cross-spectral images have been widely used in computer vision and image processing. Therefore, an effective super-resolution (SR) method provides high-resolution (HR) cross-spectral images for different research and applications. However, existing SR methods rarely consider utilizing cross-spectral information to assist the SR of visible images. They cannot handle complex degradation (noise, high brightness, low light) and misalignment problems in low-resolution (LR) cross-spectral images. Here, we first explore the potential of using near-infrared (NIR) image guidance for better SR, based on the observation that NIR images can preserve valuable information for recovering adequate image details. To take full advantage of the cross-spectral prior, we propose a novel Cross-Spectral Prior guided image SR approach (CSPSR). The cross-view matching (CVM) module and the dynamic multi-modal fusion (DMF) module can enhance the spatial correlation between cross-spectral images and bridge the multi-modal feature gap, respectively. Extensive experiments demonstrate the effectiveness of our CSPSR. © 2024 ACM.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Multi-channel generation of vortex beams with controllable polarization states and orbital angular momentum

引用

Chinese Physics B 2023年第12期32卷 90-97页

作者：吕子瑶王潘王长顺 State Key Laboratory of Advanced Optical Communication Systems and Networks School of Physics and AstronomyShanghai Jiao Tong UniversityShanghai 200240China School of Data Science The Chinese University of Hong KongShenzhen 518172China

Optical vortices with tunable polarization states and topological charges are widely investigated in various physical systems and practical devices for high-capacity optical ***,this kind of structured light beams is usually generated using several polarization and spatial phase devices,which decreases the configurability of optical ***,we have designed a kind of polarized optical multi-vortices generator based on the Stokes-Mueller formalism and cross-phase *** our scheme,multi-channel generation of polarized vortex beams can be realized through a single optical element and a single-input Gaussian *** polarization states and orbital angular momentum of the generated light beams are all-optically ***,the proposed polarized optical multi-vortices generator has also been demonstrated experimentally through one-step holographic recording in an azobenzene liquid-crystalline film and the experimental results agree with theoretical analysis.

关键词： light field modulation holography optical vortex polarization

来源：评论

学校读者我要写书评

暂无评论

FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse dataset and a Decomposed Model 24

FacialFlowNet: Advancing Facial Optical Flow Estimation with...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Lu, Jianzhi He, Ruian Zhou, Shili Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400706868

Facial movements play a crucial role in conveying altitude and intentions, and facial optical flow provides a dynamic and detailed representation of it. However, the scarcity of datasets and a modern baseline hinders the progress in facial optical flow research. This paper proposes FacialFlowNet (FFN), a novel large-scale facial optical flow dataset, and the Decomposed Facial Flow Model (DecFlow), the first method capable of decomposing facial flow. FFN comprises 9,635 identities and 105,970 image pairs, offering unprecedented diversity for detailed facial and head motion analysis. DecFlow features a facial semantic-aware encoder and a decomposed flow decoder, excelling in accurately estimating and decomposing facial flow into head and expression components. Comprehensive experiments demonstrate that FFN significantly enhances the accuracy of facial flow estimation across various optical flow methods, achieving up to an 11% reduction in Endpoint Error (EPE) (from 3.91 to 3.48). Moreover, DecFlow, when coupled with FFN, outperforms existing methods in both synthetic and real-world scenarios, enhancing facial expression analysis. The decomposed expression flow achieves a substantial accuracy improvement of 18% (from 69.1% to 82.1%) in micro-expressions recognition. These contributions represent a significant advancement in facial motion analysis and optical flow estimation. Codes and datasets can be found here. © 2024 ACM.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance for Class Incremental Learning in Medical Image Classification 24

Addressing Imbalance for Class Incremental Learning in Medic...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Hao, Xuze Ni, Wenqian Jiang, Xuhao Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400706868

Deep convolutional neural networks have made significant breakthroughs in medical image classification, under the assumption that training samples from all classes are simultaneously available. However, in real-world medical scenarios, there's a common need to continuously learn about new diseases, leading to the emerging field of class incremental learning (CIL) in the medical domain. Typically, CIL suffers from catastrophic forgetting when trained on new classes. This phenomenon is mainly caused by the imbalance between old and new classes, and it becomes even more challenging with imbalanced medical datasets. In this work, we introduce two simple yet effective plug-in methods to mitigate the adverse effects of the imbalance. First, we propose a CIL-balanced classification loss to mitigate the classifier bias toward majority classes via logit adjustment. Second, we propose a distribution margin loss that not only alleviates the inter-class overlap in embedding space but also enforces the intra-class compactness. We evaluate the effectiveness of our method with extensive experiments on three benchmark datasets (CCH5000, HAM10000, and EyePACS). The results demonstrate that our approach outperforms state-of-the-art methods. © 2024 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Medical data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models 24

A Medical Data-Effective Learning Benchmark for Highly Effic...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yang, Wenxuan Tan, Weimin Sun, Yuqi Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400706868

Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper introduces data-effective learning, aiming to use data in the most impactful way to pre-train foundation models. This involves strategies that focus on data quality rather than quantity, ensuring the data used for training has high informational value. data-effective learning plays a profound role in accelerating foundation model training, reducing computational costs, and saving data storage, which is very important as the volume of medical data in recent years has grown beyond many people's expectations. However, due to the lack of standards and comprehensive benchmark, research on medical data-effective learning is poorly studied. To address this gap, our paper introduces a comprehensive benchmark specifically for evaluating data-effective learning in the medical field. This benchmark includes a dataset with millions of data samples from 31 medical centers (dataDEL), a baseline method for comparison (MedDEL), and a new evaluation metric (NormDEL) to objectively measure data-effective learning performance. Our extensive experimental results show the baseline MedDEL can achieve performance comparable to the original large dataset with only 5% of the data. Establishing such an open data-effective learning benchmark is crucial for the medical foundation model research community because it facilitates efficient data use, promotes collaborative breakthroughs, and fosters the development of cost-effective, scalable, and impactful healthcare solutions. The benchmark can be accessed at https://***/shadow2469/*** GitHub Repository. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Character Prediction for Text Generation

Federated Learning for Character Prediction for Text Generat...

引用

2023 Congress in computer science, computer Engineering, and Applied Computing, CSCE 2023

作者： Hu, Guang Fang, Xin School of Statistics and Information Shanghai University of International Business and Economics Shanghai China School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China

ISBN: (纸本)9798350327595

Modern mobile devices have access to enormous amounts of user data including text, images, speech, etc., which can be utilized to train high-performance learning models and enhance the user experience. However, accessing large amounts of data often raises concerns for user privacy and security. To address this, federated learning (FL) has emerged as a new machine learning approach that trains models on multiple decentralized edge devices (e. g. mobiles) or servers while protecting user privacy. In this paper, we present a distributed learning framework using a practical iterative average-based federated learning algorithm for the text generation task in Natural Language Processing (NLP). Our results show that text generation training under federated learning yields better performance than random guessing, demonstrating the feasibility of FL in language modeling. The study highlights the success of text generation techniques trained using federated learning, while emphasizing the importance of safeguarding user privacy and security. © 2023 IEEE.

关键词： FedAvg Federated Learning Natural Language Processing Text Generation

来源：评论

学校读者我要写书评

暂无评论

Improved Machine Learning Approach for shanghai City's Secondhand Housing Price Prediction

Improved Machine Learning Approach for Shanghai City's Secon...

引用

2023 Congress in computer science, computer Engineering, and Applied Computing, CSCE 2023

作者： Hu, Guang Tang, Yue Yi, Rui School of Statistics and Information Shanghai University of International Business and Economics Shanghai China School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science Shanghai China

ISBN: (纸本)9798350327595

This paper presents an improved machine learning approach for prediction of second-hand housing prices in shanghai. It firstly builds the random forest model and the XGboost model with shanghai second-hand housing transaction data, and then analyses the challenges in the improvement of the models' prediction accuracy and generalization performance. In the light of that, it introduces the Lasso model for variable selection, and deletes three variables with insignificant regression coefficients, and then rebuilds the random forest and XGboost prediction models. The experimental results show that the prediction accuracy and the generalization performance of the models is well improved. © 2023 IEEE.

关键词： Lasso Machine Learning Prediction Random Forest XGboost

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Learning for Fine-Grained Entity Typing with Mixed Label Smoothing and Pseudo Labeling 28th

Semi-supervised Learning for Fine-Grained Entity Typing wit...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Xu, Bo Zhang, Zhengqi Du, Ming Wang, Hongya Song, Hui Xiao, Yanghua School of Computer Science and Technology Donghua University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Fudan-Aishu Cognitive Intelligence Joint Research Center Shanghai China

ISBN: (纸本)9783031306747

Distant supervision (DS) has been proposed to automatically annotate data and achieved significant success in fine-grained entity typing(FET). Despite its efficiency, distant supervision often suffers from the noisy labeling problem. To solve the noisy labeling problem, existing approaches assume the existence of "clean" and "noisy" sets in the training data and use different types of methods to utilize them. However, they still suffer from the confirmation bias problem in the "noisy" set and the false positive problem in the "clean" set. To address these issues, we propose a novel semi-supervised learning method with mixed label smoothing and pseudo labeling for distantly supervised fine-grained entity typing. Specifically, to solve the false positive problem on the "clean" set, we propose a mixed label smoothing method to smooth the labels of the "clean" set to train the FET model. To solve the confirmation bias problem on the "noisy" set, we do not consider the labels in the "noisy" set and use a pseudo labeling technique to deal with the "noisy" set. Extensive experiments conducted on three widely used FET datasets show the effectiveness of our proposed approach. The source code is publicly available at https://***/xubodhu/NFETC-SSL. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning systems

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：