检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Fu, Kexue Luo, Xiaoyuan Qu, Linhao Wang, Shuo Xiong, Ying Maglogiannis, Ilias Gao, Longxiang Wang, Manning Qilu University of Technology Shandong Academy of Sciences Jinan China Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China Fudan University China University of Piraeus Greece Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22% annotation costs. All codes and models will be publicly available on https://***/fukexue/FAST. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boosting Point-BERT by Multi-choice Tokens

arXiv

引用

arXiv 2022年

作者： Fu, Kexue Yuan, Mingzhi Wang, Manning Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai China

Masked language modeling (MLM) has become one of the most successful self-supervised pre-training task. Inspired by its success, Point-BERT, as a pioneer work in point cloud, proposed masked point modeling (MPM) to pre-train point transformer on large scale unanotated dataset. Despite its great performance, we find the inherent difference between language and point cloud tends to cause ambiguous tokenization for point cloud. For point cloud, there doesn’t exist a gold standard for point cloud tokenization. Point-BERT use a discrete Variational AutoEncoder (dVAE) as tokenizer, but it might generate different token ids for semantically-similar patches and generate the same token ids for semantically-dissimilar patches. To tackle above problem, we propose our McP-BERT, a pre-training framework with multi-choice tokens. Specifically, we ease the previous single-choice constraint on patch token ids in Point-BERT, and provide multi-choice token ids for each patch as supervision. Moreover, we utilitze the high-level semantics learned by transformer to further refine our supervision signals. Extensive experiments on point cloud classification, few-shot classification and part segmentation tasks demonstrate the superiority of our method, e.g., the pre-trained transformer achieves 94.1% accuracy on ModelNet40, 84.28% accuracy on the hardest setting of ScanObjectNN and new state-of-the-art performance on few-shot learning. We also demonstrate that our method not only improves the performance of Point-BERT on all downstream tasks, but also incurs almost no extra computational overhead. The code will be released in https://***/fukexue/McP-BERT. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Dual Attention Poser: Dual Path Body Tracking Based on Attention

Dual Attention Poser: Dual Path Body Tracking Based on Atten...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Xinhan Di Xiaokun Dai Xinkang Zhang Xinrong Chen Deepearthgo Academy for Engineering&Technology Fudan Universiry Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Fudan University

Currently, mixed reality head-mounted displays tracking the full body of users is an important human-computer interaction mode through the pose of the head and the hands. Unfortunately, users’ virtual representation and experience is limited due to high reconstruction error when simple transformer network architecture is applied. In this paper, we present a novel model, named Dual Attention Poser, which can learn the whole body reconstruction at a high accuracy. The proposed model consists of three key modules. Among them, dual-path attention encoder is designed to extract feature of the sparse signals. Cross attention mixer module enable the fusion of representation in the double path. Attention-gated-mlp decoder is applied to decode the hidden feature from the sparse input through attention gate. Test results on the AMASS dataset show that Dual Attention Poser can reduce the error by up to 18.2% in comparison with the state-of-the-art results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution

arXiv

引用

arXiv 2024年

作者： Duan, Minghong Qu, Linhao Liu, Shaolei Wang, Manning Digital Medical Research Center Fudan University Shanghai China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China

Implicit neural representations have recently demonstrated promising potential in arbitrary-scale Super-Resolution (SR) of images. Most existing methods predict the pixel in the SR image based on the queried coordinate and ensemble nearby features, overlooking the importance of incorporating high-frequency prior information in images, which results in limited performance in reconstructing high-frequency texture details in images. To address this issue, we propose the Local Implicit Wavelet Transformer (LIWT) to enhance the restoration of high-frequency texture details. Specifically, we decompose the features extracted by an encoder into four sub-bands containing different frequency information using Discrete Wavelet Transform (DWT). We then introduce the Wavelet Enhanced Residual Module (WERM) to transform these four sub-bands into high-frequency priors, followed by utilizing the Wavelet Mutual Projected Fusion (WMPF) and the Wavelet-aware Implicit Attention (WIA) to fully exploit the high-frequency prior information for recovering high-frequency details in images. We conducted extensive experiments on benchmark datasets to validate the effectiveness of LIWT. Both qualitative and quantitative results demonstrate that LIWT achieves promising performance in arbitrary-scale SR tasks, outperforming other state-of-the-art methods. The code is available at https://***/dmhdmhdmh/LIWT. Copyright © 2024, The Authors. All rights reserved.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Rethinking Multiple Instance Learning: Developing an Instance-Level Classifier via Weakly-Supervised Self-Training

arXiv

引用

arXiv 2024年

作者： Ma, Yingfan Luo, Xiaoyuan Yuan, Mingzhi Chen, Xinrong Wang, Manning The Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China The Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance. For example, existing methods often face difficulty in learning hard positive instances. In this paper, we formulate MIL as a semi-supervised instance classification problem, so that all the labeled and unlabeled instances can be fully utilized to train a better classifier. The difficulty in this formulation is that all the labeled instances are negative in MIL, and traditional self-training techniques used in semi-supervised learning tend to degenerate in generating pseudo labels for the unlabeled instances in this scenario. To resolve this problem, we propose a weakly-supervised self-training method, in which we utilize the positive bag labels to construct a global constraint and a local constraint on the pseudo labels to prevent them from degenerating and force the classifier to learn hard positive instances. It is worth noting that easy positive instances are instances are far from the decision boundary in the classification process, while hard positive instances are those close to the decision boundary. Through iterative optimization, the pseudo labels can gradually approach the true labels. Extensive experiments on two MNIST synthetic datasets, five traditional MIL benchmark datasets and two histopathology whole slide image datasets show that our method achieved new SOTA performance on all of them. The code will be publicly available. Impact Statement-MIL is a primary research field within weakly supervised learning and has numerous applications, such as histopathology analysis, video anomaly detection, and drug design. However, current mainstream methods in MIL predominantly rely on bag labels to train the network, consequently overlooking the potential of instance-level supervision information. In our paper, we highlight the

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Ddfp: Data-Dependent Frequency Prompt for Source Free Domain Adaptation of medical image Segmentation

SSRN

引用

SSRN 2024年

作者： Yin, Siqi Liu, Shaolei Wang, Manning Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

Domain adaptation aims to address model performance degradation problem under domain gap. In the typical setting of unsupervised domain adaptation, labeled data from source domain and unlabeled data from target domain are used to train a target model. However, access to source domain medical data can be restricted due to privacy policies, in which scenario, the research attention has shifted to source free domain adaptation (SFDA) which only requires a trained source domain model and unlabeled target domain data for adaptation. Existing SFDA methods often utilize domain-dependent image style translation and self-supervision techniques to reduce domain gap and train the target domain model. However, the quality of domain-dependent style translated images and pseudo labels still leaves room for improvement. Moreover, training the entire model during adaptation is suboptimal under limited supervision. In this paper, we propose a novel SFDA framework to overcome these limitations. Specifically, to effectively mitigate the impact of domain gap in the initial training phase, we introduce pre-adaptation to derive a pre-adapted model for target model initialization and generate quality enhanced pseudo labels without introducing additional parameters. Furthermore, we propose a data-dependent frequency prompt to better translate target domain images into a source-like style individually. Subsequently, the style-related layers fine-tuning strategy tailored for SFDA is used to train the target model using the prompted target domain images and pseudo labels. Extensive experiments on cross-modality abdominal and cardiac SFDA segmentation tasks demonstrated that our proposed method outperforms the state-of-the-art baselines. Our code is available online. © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version)

arXiv

引用

arXiv 2022年

作者： Fu, Kexue Luo, Jiazheng Luo, Xiaoyuan Liu, Shaolei Zhang, Chenxi Wang, Manning The Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China The Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

3D point cloud registration is a fundamental problem in computer vision and robotics. Recently, learning-based point cloud registration methods have made great progress. However, these methods are sensitive to outliers, which lead to more incorrect correspondences. In this paper, we propose a novel deep graph matching-based framework for point cloud registration. Specifically, we first transform point clouds into graphs and extract deep features for each point. Then, we develop a module based on deep graph matching to calculate a soft correspondence matrix. By using graph matching, not only the local geometry of each point but also its structure and topology in a larger range are considered in establishing correspondences, so that more correct correspondences are found. We train the network with a loss directly defined on the correspondences, and in the test stage the soft correspondences are transformed into hard one-to-one correspondences so that registration can be performed by a correspondence-based solver. Furthermore, we introduce a transformer-based method to generate edges for graph construction, which further improves the quality of the correspondences. Extensive experiments on object-level and scene-level benchmark datasets show that the proposed method achieves state-of-the-art performance. The code is available at: https://***/fukexue/RGM. Copyright © 2022, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

The rise of AI language pathologists: exploring two-level prompt learning for few-shot weakly-supervised whole slide image classification 23

The rise of AI language pathologists: exploring two-level pr...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Linhao Qu Xiaoyuan Luo Kexue Fu Manning Wang Zhijian Song Digital Medical Research Center School of Basic Medical Science Fudan University and Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention

This paper introduces the novel concept of few-shot weakly supervised learning for pathology Whole Slide image (WSI) classification, denoted as FSWC. A solution is proposed based on prompt learning and the utilization of a large language model, GPT-4. Since a WSI is too large and needs to be divided into patches for processing, WSI classification is commonly approached as a Multiple Instance Learning (MIL) problem. In this context, each WSI is considered a bag, and the obtained patches are treated as instances. The objective of FSWC is to classify both bags and instances with only a limited number of labeled bags. Unlike conventional few-shot learning problems, FSWC poses additional challenges due to its weak bag labels within the MIL framework. Drawing inspiration from the recent achievements of vision-language models (V-L models) in downstream few-shot classification tasks, we propose a two-level prompt learning MIL framework tailored for pathology, incorporating language prior knowledge. Specifically, we leverage CLIP to extract instance features for each patch, and introduce a prompt-guided pooling strategy to aggregate these instance features into a bag feature. Subsequently, we employ a small number of labeled bags to facilitate few-shot prompt learning based on the bag features. Our approach incorporates the utilization of GPT-4 in a question-and-answer mode to obtain language prior knowledge at both the instance and bag levels, which are then integrated into the instance and bag level language prompts. Additionally, a learnable component of the language prompts is trained using the available few-shot labeled data. We conduct extensive experiments on three real WSI datasets encompassing breast cancer, lung cancer, and cervical cancer, demonstrating the notable performance of the proposed method in bag and instance classification. Codes will be available at https://***/miccaiif/TOP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

POS-BERT: Point Cloud One-Stage BERT Pre-Training

arXiv

引用

arXiv 2022年

作者： Fu, Kexue Gao, Peng Liu, Shaolei Zhang, Renrui Qiao, Yu Wang, Manning Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai AI Lab China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention China

Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, directly extending BERT from NLP to point clouds requires training a fixed discrete Variational AutoEncoder (dVAE) before pre-training, which results in a complex two-stage method called Point-BERT. Inspired by BERT and MoCo, we propose POS-BERT, a one-stage BERT pre-training method for point clouds. Specifically, we use the mask patch modeling (MPM) task to perform point cloud pre-training, which aims to recover masked patches information under the supervision of the corresponding tokenizer output. Unlike Point-BERT, its tokenizer is extra-trained and frozen. We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process. Further, in order to learn high-level semantic representation, we combine contrastive learning to maximize the class token consistency between different transformation point clouds. Extensive experiments have demonstrated that POS-BERT can extract high-quality pre-training features and promote downstream tasks to improve performance. Using the pretraining model without any fine-tuning to extract features and train linear SVM on ModelNet40, POS-BERT achieves the state-of-the-art classification accuracy, which exceeds Point-BERT by 3.5%. In addition, our approach has significantly improved many downstream tasks, such as fine-tuned classification, few-shot classification, part segmentation. The code and trained-models will be available at: https://***/fukexue/POS-BERT. Copyright © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Boosting Whole Slide image Classification from the Perspectives of Distribution, Correlation and Magnification

Boosting Whole Slide Image Classification from the Perspecti...

引用

International Conference on computer Vision (ICCV)

作者： Linhao Qu Zhiwei Yang Minghong Duan Yingfan Ma Shuo Wang Manning Wang Zhijian Song Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention

Bag-based multiple instance learning (MIL) methods have become the mainstream for Whole Slide image (WSI) classification. However, there are still three important issues that have not been fully addressed: (1) positive bags with a low positive instance ratio are prone to the influence of a large number of negative instances; (2) the correlation between local and global features of pathology images has not been fully modeled; and (3) there is a lack of effective information interaction between different magnifications. In this paper, we propose MILBooster, a powerful dual-scale multi-stage MIL framework to address these issues from the perspectives of distribution, correlation, and magnification. Specifically, to address issue (1), we propose a plug-and-play bag filter that effectively increases the positive instance ratio of positive bags. For issue (2), we propose a novel window-based Transformer architecture called PiceBlock to model the correlation between local and global features of pathology images. For issue (3), we propose a dual-branch architecture to process different magnifications and design an information interaction module called Scale Mixer for efficient information interaction between them. We conducted extensive experiments on four clinical WSI classification tasks using three datasets. MILBooster achieved new state-of-the-art performance on all these tasks. Codes will be available at https://***/miccaiif/MILBooster.

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：