检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Lei, Wenhui Xu, Wei Li, Kang Zhang, Xiaofan Zhang, Shaoting School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Shanghai AI Lab Shanghai China School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei China West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu China

Recent advancements in foundation models have shown significant potential in medical image analysis. However, there is still a gap in models specifically designed for medical image localization. To address this, we introduce MedLAM, a 3D medical foundation localization model that accurately identifies any anatomical part within the body using only a few template scans. MedLAM employs two self-supervision tasks: unified anatomical mapping (UAM) and multi-scale similarity (MSS) across a comprehensive dataset of 14,012 CT scans. Furthermore, we developed MedLSAM by integrating MedLAM with the Segment Anything Model (SAM). This innovative framework requires extreme point annotations across three directions on several templates to enable MedLAM to locate the target anatomical structure in the image, with SAM performing the segmentation. It significantly reduces the amount of manual annotation required by SAM in 3D medical imaging scenarios. We conducted extensive experiments on two 3D datasets covering 38 distinct organs. Our findings are twofold: 1) MedLAM can directly localize anatomical structures using just a few template scans, achieving performance comparable to fully supervised models;2) MedLSAM closely matches the performance of SAM and its specialized medical adaptations with manual prompts, while minimizing the need for extensive point annotations across the entire dataset. Moreover, MedLAM has the potential to be seamlessly integrated with future 3D SAM models, paving the way for enhanced segmentation performance. Our code is public at https://***/openmedlab/MedLSAM. © 2023, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

SoLar: sinkhorn label refinery for imbalanced partial-label learning 22

SoLar: sinkhorn label refinery for imbalanced partial-label ...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Haobo Wang Mingxuan Xia Yixuan Li Yuren Mao Lei Feng Gang Chen Junbo Zhao Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University School of Software Technology Zhejiang University Department of Computer Sciences University of Wisconsin-Madison College of Computer Science Chongqing University and Center for Advanced Intelligence Project RIKEN

ISBN: (纸本)9781713871088

Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods have been proposed in this domain, they normally assume a class-balanced scenario that may not hold in many real-world applications. Empirically, we observe degenerated performance of the prior methods when facing the combinatorial challenge from the long-tailed distribution and partial-labeling. In this work, we first identify the major reasons that the prior work failed. We subsequently propose SoLar, a novel Optimal Transport-based framework that allows to refine the disambiguated labels towards matching the marginal class prior distribution. SoLar additionally incorporates a new and systematic mechanism for estimating the long-tailed class prior distribution under the PLL setup. Through extensive experiments, SoLar exhibits substantially superior results on standardized benchmarks compared to the previous state-of-the-art PLL methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolutional Transformer with Similarity-based Boundary Prediction for Action Segmentation

Convolutional Transformer with Similarity-based Boundary Pre...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Dazhao Du Bing Su Yu Li Zhongang Qi Lingyu Si Ying Shan Institute of Software Chinese Academy of Science University of Chinese Academy of Sciences Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods International Digital Economy Academy Tencent PCG ARC Lab

Action classification has made great progress, but segmenting and recognizing actions from long videos remains a challenging problem. Recently, Transformer-based models with strong sequence modeling ability have succeeded in many se-quence modeling tasks. However, the lack of inductive bias and the difficulty of handling long video sequences limit the application of the Transformer in the action segmentation task. In order to explore the potential of the Transformer in this task, we replace some specific linear layers in the vanilla Transformer with dilated temporal convolution, and a sparse attention mechanism is utilized to reduce the time and space complexities to process long video sequences. Besides, directly using frame-wise classification loss to train the model will cause that frames at boundaries of actions are treated equally with those in the middle of actions, and the learned features are not sensitive to boundaries. We propose a new local log-context attention module to predict whether each frame is at the beginning, middle, or end of an action. Since boundary frames are similar to their neighboring frames of different classes, our similarity-based boundary prediction helps learn more discriminative features. Extensive experiments on three datasets show the effectiveness of our method.

关键词： Convolution Video sequences Predictive models Transformers Complexity theory Convolutional neural networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring the common principal subspace of deep features in neural networks

arXiv

引用

arXiv 2021年

作者： Liu, Haoran Xiong, Haoyi Wang, Yaqing An, Haozhe Wu, Dongrui Dou, Dejing Big Data Lab Baidu Research Department of Computer Science University of Maryland College ParkMD United States School of Artificial Intelligence and Automation Huazhong University of Science and Technology

We find that different Deep Neural Networks (DNNs) trained with the same dataset share a common principal subspace in latent spaces, no matter in which architectures (e.g., Convolutional Neural Networks (CNNs), Multi-Layer Preceptors (MLPs) and Autoencoders (AEs)) the DNNs were built or even whether labels have been used in training (e.g., supervised, unsupervised, and self-supervised learning). Specifically, we design a new metric P-vector to represent the principal subspace of deep features learned in a DNN, and propose to measure angles between the principal subspaces using P- vectors. Small angles (with cosine close to 1.0) have been found in the comparisons between any two DNNs trained with different algorithms/architectures. Furthermore, during the training procedure from random scratch, the angle decrease from a larger one (70°-80° usually) to the small one, which coincides the progress of feature space learning from scratch to convergence. Then, we carry out case studies to measure the angle between the P-vector and the principal subspace of training dataset, and connect such angle with generalization performance. Extensive experiments with practically-used Multi-Layer Perceptron (MLPs), AEs and CNNs for classification, image reconstruction, and self-supervised learning tasks on MNIST, CIFAR-10 and CIFAR-100 datasets have been done to support our claims with solid evidences. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatically derived stateful network functions including non-field attributes

Automatically derived stateful network functions including n...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Bin Yuan Shengyao Sun Xianjun Deng Deqing Zou Haoyu Chen Shenghui Li Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Shenzhen Research Institute Huazhong University of Science and Technology Shenzhen China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Cluster and Grid Computing Lab

ISBN: (纸本)9781665416597

The modern network consists of thousands of network devices from different suppliers that perform distinct code-pendent functions, such as routing, switching, modifying header fields, and access control across physical and virtual networks. Because of the network complexity, the network is prone to a wide range of errors, such as false-positive configuration, software errors, or unexpected interactions across protocols. These errors can lead to loops, sub-optimal routing, path leaks, black holes, and access control violations that make services unavailable, vulnerable to exploitation, or prone to attacks (e.g., DDoS attacks). To mitigate these problems, network operators deploy many different stateful network functions, like firewalls, NATs, load balancers, and intrusion-prevention boxes. They have become an important part of networks today, so it is critical to verify that these network functions are the same as expected deployments. All static network verification tools are meant to rigorously check network software or configuration for bugs before deployment. They usually use handwritten models or limited derivation models that are error-prone and ignore the fact that even the same type of network functions (from different vendors) still have different implementation details. In this paper, we propose a tool that can automatically synthesize more realistic and high-fidelity models that include stateful network functions with non-field attributes. We design an inferring algorithm, implement the transformation between data packages and symbolic packages, and obtain a finite state machine that can accurately express the actions of black-box network functions for a given configuration.

关键词： Access control Performance evaluation Privacy Protocols Computational modeling Switches Routing

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

JERALD: high-fidelity dark matter, stellar mass and neutral hydrogen maps from fast N-body simulations

arXiv

引用

arXiv 2025年

作者： Rigo, Mauro Trotta, Roberto Viel, Matteo Theoretical and Scientific Data Science SISSA Via Bonomea 265 Trieste34136 Italy INFN National Institute for Nuclear Physics Via Valerio 2 Trieste34127 Italy ICSC Centro Nazionale di Ricerca in High Performance Computing Big Data e Quantum Computing Via Magnanelli 2 Bologna Italy Astrophysics Group Physics Department Blackett Lab Imperial College London Prince Consort Road LondonSW7 2AZ United Kingdom INAF Osservatorio Astronomico di Trieste Via G. B. Tiepolo 11 TriesteI-34143 Italy

We present a new code and approach, JERALD—JAX Enhanced Resolution Approximate Lagrangian Dynamics—, that improves on and extends the Lagrangian Deep Learning method of Dai & Seljak (2021), producing high-resolution dark matter, stellar mass and neutral hydrogen maps from lower-resolution approximate N-body simulations. The model is trained using the Sherwood-Relics simulation suite (for a fixed cosmology), specifically designed for the intergalactic medium and the neutral hydrogen distribution in the cosmic web. The output is tested in the redshift range from z = 5 to z = 0 and the generalization properties of the learned mapping is demonstrated. JERALD produces maps with dark matter, stellar and neutral hydrogen power spectra in excellent agreement with full-hydrodynamic simulations with 8× higher resolution, at large and intermediate scales;in particular, JERALD’s neutral hydrogen power spectra agree with their higher-resolution full-hydrodynamic counterparts within 90% up to k 1 hMpc−1 and within 70% up to k 10 hMpc−1. JERALD provides a fast, accurate and physically motivated approach that we plan to embed in a statistical inference pipeline, such as Simulation-Based Inference, to constrain dark matter properties from large- to intermediate-scale structure observables. Copyright © 2025, The Authors. All rights reserved.

关键词： Dark Matter

来源：评论

学校读者我要写书评

暂无评论

Syntax-enhanced pre-trained model 59

Syntax-enhanced pre-trained model

引用

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781954085527

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. © 2021 Association for Computational Linguistics

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

A Universal data-Driven Spatial Interpolation Framework for the Measurements of Environmental Sites

SSRN

引用

SSRN 2023年

作者： Cheng, Zhen Guo, Yuzhe Xue, Wenbo Du, Qinyi Shanghai Environmental Protection Key Lab of Environmental Big Data and Intelligent Decision-making School of Environmental Science and Engineering Shanghai Jiao Tong University Shanghai China Center of Air Quality Simulation and System Analysis Chinese Academy of Environmental Planning Beijing100043 China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

The accurate spatial distribution of environmental pollutant metrics is crucial for evaluating human exposure and managing the environment. Spatial interpolation, which relies on the measurements of limited environmental sites, is often necessary. However, commonly used geostatistical methods often introduce significant prediction biases, leading to misleading assessments and decision-making processes. Reported machine learning studies usually required intensive spatial datasets and sites’ measurements, as well as special complex algorithm for target pollutant. In this study, we propose and validate a simple and universal data-driven spatial interpolation framework for environmental sites’ measurements. We employ a conditional generative adversarial network (cGAN) as the data-driven algorithm to leverage spatial dataset. We demonstrate the implementation and validation of the framework using two representative ambient pollutants, namely ozone and PM2.5. The results reveal a relative mean absolute error of only 9% for ozone and 13% for PM2.5. Compared to the traditional inverse distance weight method and ordinary kriging method, the proposed framework reduces errors by 70% and 79% respectively. Furthermore, the R-squared values between independent measurements from additional geographic locations and the corresponding predicted results using the proposed method reach 0.96 for ozone and 0.97 for PM2.5, showcasing its excellent and consistent performance. The unique input dataset and universal algorithm architecture illustrate the distinct advantages compared to previous machine learning studies. With the rapid increase of remote sensing and numerical modeling datasets in the environmental field, we anticipate that data-driven methods will replace traditional mathematical approaches. This study provides a simple yet universal interpolation framework and is expected to accelerate the adoption of these advancements. © 2023, The Authors. All rights reserved.

关键词： Spatial distribution

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：