检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Chen, Zixuan Yang, Lingxiao Lai, Jian-Huang Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Medical image arbitrary-scale super-resolution (MIASSR) has recently gained widespread attention, aiming to supersample medical volumes at arbitrary scales via a single model. However, existing MIASSR methods face two major limitations: (i) reliance on high-resolution (HR) volumes and (ii) limited generalization ability, which restricts their applications in various scenarios. To overcome these limitations, we propose Cube-based Neural Radiance Field (CuNeRF), a zero-shot MIASSR framework that is able to yield medical images at arbitrary scales and free viewpoints in a continuous domain. Unlike existing MISR methods that only fit the mapping between low-resolution (LR) and HR volumes, CuNeRF focuses on building a continuous volumetric representation from each LR volume without the knowledge of the corresponding HR one. This is achieved by the proposed differentiable modules: cube-based sampling, isotropic volume rendering, and cube-based hierarchical rendering. Through extensive experiments on magnetic resource imaging (MRI) and computed tomography (CT) modalities, we demonstrate that CuNeRF can synthesize high-quality SR medical images, which outperforms state-of-the-art MISR methods, achieving better visual verisimilitude and fewer objectionable artifacts. Compared to existing MISR methods, our CuNeRF is more applicable in practice. Copyright © 2023, The Authors. All rights reserved.

关键词： Volume rendering

来源：评论

学校读者我要写书评

暂无评论

Discriminative Gradient Adjustment with Coupled Knowledge Distillation for Class Incremental Learning

Discriminative Gradient Adjustment with Coupled Knowledge Di...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Hao Zhang Yanxu Hu Jiawen Peng Andy J Ma School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing China

Class Incremental Learning (CIL) is a promising approach to addressing the catastrophic forgetting problem when learning for new categories. Though recent works based on dynamic architectures achieve convincing performance, data imbalance caused by limited size of memory and compression of the increasingly growing network are challenges to be solved. In this paper, we propose the novel Discriminative Gradient Adjustment (DGA) and Coupled Knowledge Distillation strategy (CKD) for these two challengs. The DGA mitigates the data imbalance problem by designing the loss function with a static global balance factor and a ground-truth-based dynamic factor. The CKD fully utilizes intermediate layers of the dual-branch models by feature-level distillation with moving-average weight updating for network compression. Extensive experiments on CIFAR100 and ImageNet100 datasets demonstrate the superiority of our method for CIL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor

arXiv

引用

arXiv 2022年

作者： Yang, Yang Cui, Zhiying Xu, Junjie Zhong, Changhong Zheng, Wei-Shi Wang, Ruixuan School of Computer Science and Engineering Sun Yat-Sen University China Key Laboratory of Machine Intelligence and Advanced Computing MOE China

Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly in intelligent diagnosis systems where initially only training data of a limited number of diseases are available. In this case, updating the intelligent system with data of new diseases would inevitably downgrade its performance on previously learned diseases. Inspired by the process of learning new knowledge in human brains, we propose a Bayesian generative model for continual learning built on a fixed pre-trained feature extractor. In this model, knowledge of each old class can be compactly represented by a collection of statistical distributions, e.g. with Gaussian mixture models, and naturally kept from forgetting in continual learning over time. Unlike existing class-incremental learning methods, the proposed approach is not sensitive to the continual learning process and can be additionally well applied to the data-incremental learning scenario. Experiments on multiple medical and natural image classification tasks showed that the proposed approach outperforms state-of-the-art approaches which even keep some images of old classes during continual learning of new classes. © 2022, CC BY.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Memory-Guided Contrastive and Triplet Separation for Weakly-Supervised Disease Detection

Memory-Guided Contrastive and Triplet Separation for Weakly-...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jinwen She Qiong Li Andy J. Ma School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Cancer Center Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Weakly-supervised disease detection has the great potential to alleviate the time-consuming and labor-intensive burden of manual annotations in instance level. While existing methods extract normality prototypes encoding normal patterns to improve the detection performance, they may fail to detect subtle anomalies without considering the diverse abnormal patterns. In this paper, we propose to recognize both normal and abnormal patterns for feature representation learning in disease detection based on a dual memory network. To learn discriminative memory banks and classifiers, dual memory loss is incorporated with a feature magnitude separation loss for model training. With the proposed contrastive feature separation loss and triplet feature separation loss, feature discriminability is further improved to obtain a more separable decision boundary. Additionally, we collect a large-scale CT dataset to evaluate lung tumor detection. Extensive experiments on the publicly available PANDA-MIL dataset and the collected LUNG-MIL dataset demonstrate the superiority of our proposed method compared to the state-of-the-art approaches for weakly-supervised disease detection.

关键词： Training Representation learning Lung cancer Prototypes Manuals Feature extraction Encoding Pattern recognition Diseases Tumors

来源：评论

学校读者我要写书评

暂无评论

Dual Episodic Sampling and Momentum Consistency Regularization for Unsupervised Few-shot Learning

Dual Episodic Sampling and Momentum Consistency Regularizati...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jiaxin Chen Yanxu Hu Meng Shen Andy J. Ma School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Unsupervised Few-shot Learning (UFSL) is a practical approach to adapting knowledge learned from unlabeled data of base classes to novel classes with limited labeled data. Nevertheless, most existing UFSL methods may not learn generalizable features in latter training epochs due to the simplicity of meta-learning tasks constructed by data augmentation. To address this issue, we propose two novel components, namely Dual Episodic Sampling (DES) and Momentum Consistency Regularization (MCR) for UFSL. In the DES, two types of sampling strategies are used to construct harder training tasks with multiple augmentations to generate each pseudo-class of increased diversity. The MCR constrains the consistency of the backbone encoder with its momentum counterpart to learn better generalized features for novel classes. Experimental results on four datasets verify the superiority of our method for unsupervised few-shot image classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection

arXiv

引用

arXiv 2024年

作者： Liufu, Xing Tan, Chaolei Lin, Xiaotong Qi, Yonggang Li, Jinxuan Hu, Jian-Fang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China

Edge labels are typically at various granularity levels owing to the varying preferences of annotators, thus handling the subjectivity of per-pixel labels has been a focal point for edge detection. Previous methods often employ a simple voting strategy to diminish such label uncertainty or impose a strong assumption of labels with a pre-defined distribution, e.g., Gaussian. In this work, we unveil that the segment anything model (SAM) provides strong prior knowledge to model the uncertainty in edge labels. Our key insight is that the intermediate SAM features inherently correspond to object edges at various granularities, which reflects different edge options due to uncertainty. Therefore, we attempt to align uncertainty with granularity by regressing intermediate SAM features from different layers to object edges at multi-granularity levels. In doing so, the model can fully and explicitly explore diverse "uncertainties" in a data-driven fashion. Specifically, we inject a lightweight module (∼ 1.5% additional parameters) into the frozen SAM to progressively fuse and adapt its intermediate features to estimate edges from coarse to fine. It is crucial to normalize the granularity level of human edge labels to match their innate uncertainty. For this, we simply perform linear blending to the real edge labels at hand to create pseudo labels with varying granularities. Consequently, our uncertainty-aligned edge detector can flexibly produce edges at any desired granularity (including an optimal one). Thanks to SAM, our model uniquely demonstrates strong generalizability for cross-dataset edge detection. Extensive experimental results on BSDS500, Muticue and NYUDv2 validate our model’s superiority. Copyright © 2024, The Authors. All rights reserved.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medic...

引用

International Conference on Computer Vision (ICCV)

作者： Zixuan Chen Lingxiao Yang Jian-Huang Lai Xiaohua Xie School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

关键词：

来源：评论

学校读者我要写书评

暂无评论

View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network

arXiv

引用

arXiv 2024年

作者： Zhang, Quan Wang, Lei Patel, Vishal M. Xie, Xiaohua Lai, Jianhuang School of Computer Science and Engineering Sun Yat-Sen University China Guangdong China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Department of Electrical and Computer Engineering Johns Hopkins University United States

Existing person re-identification methods have achieved remarkable advances in appearance-based identity association across homogeneous cameras, such as ground-ground matching. However, as a more practical scenario, aerial-ground person re-identification (AGPReID) among heterogeneous cameras has received minimal attention. To alleviate the disruption of discriminative identity representation by dramatic view discrepancy as the most significant challenge in AGPReID, the view-decoupled transformer (VDT) is proposed as a simple yet effective framework. Two major components are designed in VDT to decouple view-related and view-unrelated features, namely hierarchical subtractive separation and orthogonal loss, where the former separates these two features inside the VDT, and the latter constrains these two to be independent. In addition, we contribute a large-scale AGPReID dataset called CARGO, consisting of five/eight aerial/ground cameras, 5,000 identities, and 108,563 images. Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5.0%/2.7% on CARGO and 3.7%/5.2% on AG-ReID, keeping the same magnitude of computational complexity. Our project is available at https://***/LinlyAC/VDT-AGPReID. © 2024, CC BY.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Region Attention Fine-tuning with CLIP for Few-shot Classification

Region Attention Fine-tuning with CLIP for Few-shot Classifi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Guangxing Wu Junxi Chen Qiu Li Wentao Zhang Wei-Shi Zheng Ruixuan Wang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China China United Network Communications Corporation Limited Guangdong Branch Guangzhou China Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

With the advancements in visual language models such as CLIP and their strong performance in zero-shot recognition, numerous CLIP-based methods have emerged in the field of few-shot classification. However, many of them do not fully leverage the abundant feature information within the CLIP visual encoder and overlook the issue of varying region-specific importance for image classification across different datasets. To address these limitations, we present an attention pooling-based framework for few-shot fine-tuning. Our framework enables the model to learn task-specific attention weights for image regions, while also incorporating background features and a consistency constraint to enhance training. As a result, our approach outperforms the state-of-the-art approaches on 11 benchmarks, demonstrating its effectiveness.

关键词： Training Visualization Benchmark testing Image classification

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Adaptive Augmentation for Knowledge Concept Recommendation

Graph Contrastive Learning with Adaptive Augmentation for Kn...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Mei Yu Zhaoyuan Ding Jian Yu Wenbin Zhang Ming Yang Mankun Zhao College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Advanced Networking(TANK Lab) Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Information and Network Center Tianjin University Tianjin China College of Computing and Software Engineering Kennesaw State University Marietta GA USA

Knowledge concept recommendation is a kind of fine-grained recommendation in massive open online courses (MOOCs) scenario, user interaction data has the characteristics of strong collaborative signals and imbalanced interactions. This leads to a single recommendation and reduced accuracy. Recently, the ability of contrastive learning (CL) in mitigating interaction imbalance in recommender systems has received widespread attention. CL requires the use of augmentation methods to generate different views. Existing augmentation methods (1) augment only at the topology or feature level ignoring semantic or structural information, and (2) undifferentiated augmentation tends to lose the critical information. In this paper, we propose Graph Contrastive Learning with Adaptive Augmentation for Knowledge Concept Recommendation (GCARec). Specifically, (1) topology level adaptive augmentation based on degree centrality captures critical structural information, and then (2) feature level adaptive augmentation based on degree centrality captures critical semantic information. Comprehensive experiments show that our proposed approach can outperform other baselines. Our implementations are available at https://***/DingZhaoyuan/GCARec.

关键词：

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：