检索结果-内蒙古大学图书馆

Snowed autoencoders are efficient snow removers

COMPUTERS & GRAPHICS-UK 2023年第1期114卷 73-85页

作者： Liu, Yifan Chen, Jincai Lu, Ping Zhu, Chuanbo Jian, Yugen Sun, Chao Liang, Han Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Engn Res Ctr Data Storage Syst & Technol Key Lab Informat Storage Syst Wuhan 430074 Peoples R China

Snow is a harsh natural phenomenon that greatly affects the performance of advanced computer vision tasks. Recently, most image desnowing methods rely on complex model structures, leading to increased carbon emissions and impossibilities to deploy on lightweight computing devices. Additionally, most deep learning-based methods do not effectively utilize the position information of snow particles, which will limit the performance of the model. To address these issues, considering that snow particles have block-shaped shape distribution and color uniformity similar to a mask, we propose a snowed autoencoder (SAE) desnowing method. Specifically, the SAE is composed of four parts: snowed masking process, SAE encoder, SAE decoder, and prediction stage. First, a snowy image is passed through the snowed masking process to generate a mask that exactly covers the snow particles and output the coordinates of the four vertices of the mask and the index of each segmented image patch. The input image and each mask coordinate and index are passed through the SAE encoder based on the snow particle attention module to generate an image representation for identifying typical features of snow particles. Then, the generated typical features of snow particles are fed into the SAE decoder to reconstruct image patches without snow. Finally, all the patches will be passed through the prediction stage to reconstruct the original size of the snow-free image. A large number of experiments show that the proposed SAE desnowing method achieves the state-of-the-art desnowing performance on three synthetic and one real-world desnowing datasets. The images after desnowing by SAE have better color details and are more consistent with human visual habits. In addition, SAE has faster desnowing speed and fewer parameters. The code is available at https://***/awhitewhale/SAE. & COPY;2023 Elsevier Ltd. All rights reserved.

关键词： Single image snow removal masked autoencoder Vision transformer

来源：评论

学校读者我要写书评

暂无评论

Research on image classification of power inspection using less sample learning technique

引用

INTERNATIONAL JOURNAL OF LOW-CARBON TECHNOLOGIES 2024年第19期19卷 2119-2126页

作者： Li, Qiang Zhuang, Li Wang, Qiulin Song, Lihua Wang, Yanrong State Grid Informat & Commun Ind Grp Co LTD Beijing 102211 Peoples R China Fujian Yirong Informat Technol Co LTD Fuzhou 350001 Peoples R China

This study proposes a few-sample self-supervised power inspection image classification method based on Vision Transformer and masked autoencoders (MAE). Initially, an MAE is employed to pretrain an extensive collection of unlabeled power inspection images, leveraging the masking technique to encourage the model to acquire an understanding of the overarching features within these images. Then, the pretrained encoder part is combined with the visual transformer to further extract image features. For the subsequent classification task, the encoder's pretrained weights are frozen and subsequently incorporated into a novel classification network. By fine-tuning this network with a limited amount of labeled data, experimental findings indicate a substantial enhancement in the classification accuracy of power inspection images, particularly in scenarios with limited sample sizes. By introducing visual transformers and MAE, this article provides an efficient and reliable solution for intelligent classification of power inspection images, which has important practical application value and broad market prospects.

关键词： power inspection visual transformer masked autoencoder few samples self-supervision

来源：评论

学校读者我要写书评

暂无评论

A Step-Wise Domain Adaptation Detection Transformer for Object Detection under Poor Visibility Conditions

引用

REMOTE SENSING 2024年第15期16卷 2722页

作者： Zhang, Gege Wang, Luping Chen, Zengping Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen 518107 Peoples R China

To address the performance degradation of cross-domain object detection under various illumination conditions and adverse weather scenarios, this paper introduces a novel method a called Step-wise Domain Adaptation DEtection TRansformer (SDA-DETR). Our approach decomposes the adaptation process into three sequential steps, progressively transferring knowledge from a labeled dataset to an unlabeled one using the DETR (DEtection TRansformer) architecture. Each step precisely reduces domain discrepancy, thereby facilitating effective transfer learning. In the initial step, a target-like domain is constructed as an auxiliary to the source domain to reduce the domain gap at the image level. Then, we adaptively align the source domain and target domain features at both global and local levels. To further mitigate model bias towards the source domain, we develop a token-masked autoencoder (t-MAE) to enhance target domain features at the semantic level. Comprehensive experiments demonstrate that the SDA-DETR outperforms several popular cross-domain object detection methods on three challenging public driving datasets.

关键词： domain adaptation detection transformer target-like domain masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

scDMAE: A Generative Denoising Model Adopted Mask Strategy for scRNA-Seq Data Recovery

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第6期28卷 3772-3780页

作者： Liu, Wei Pan, Youze Teng, Zhijie Xu, Junlin Xiangtan Univ Sch Comp Sci Xiangtan 411105 Peoples R China Wuhan Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430065 Peoples R China

The advent of single-cell RNA sequencing (scRNA-seq) technology has revolutionized gene expression studies at the single-cell level. However, the presence of technical noise and data sparsity in scRNA-seq often undermines the accuracy of subsequent analyses. Existing methods for denoising and imputing scRNA-seq data often rely on stringent assumptions about data distribution, limiting the effectiveness of data recovery. In this study, we propose the scDMAE model for denoising and recovery of scRNA-seq data. First, the model fuses gene expression features and topological features to discern the primary expression patterns of genes in cells. Then, an autoencoder with a masking strategy is used to model dropout events and separate potential noise in the data. Finally, the model incorporates the original raw data to recover the true biological expression value. By conducting experiments on various types of scRNA-Seq datasets, scDMAE demonstrates superior performance compared to other comparative methods based on six distinct evaluation metrics in downstream analysis. The scDMAE method can accurately cluster similar cell populations, identify differential genes and infer cell trajectories.

关键词： Single-cell RNA sequencing data masked autoencoder denoising data recovery

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Split Learning for Large-Scaled Vision Pre-Training

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023年 18卷 1539-1553页

作者： Wang, Zhousheng Yang, Geng Dai, Hua Rong, Chunming Nanjing Univ Posts & Telecommun Sch Telecommun & Informat Engn Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing 210023 Peoples R China Jiangsu Key Lab Big data Secur & Intelligent Proc Nanjing 210023 Peoples R China Univ Stavanger Dept Elect Engn & Comp Sci N-4036 Stavanger Norway

The growing concerns about data privacy in society lead to restrictions on the computer vision research gradually. Several collaboration-based vision learning methods have recently emerged, e.g., federated learning and split learning. These methods protect user data from leaving local devices, and make training performed only by uploading gradients, parameters, or activations, etc. However, there is little research on collaborative learning based on state-of-the-art and large-scaled models, mainly due to the high computation or communication overheads of the latest models. Training these models may be still unrealized for users' terminals. In this paper, we make a first attempt at the sensitive image pre-training with large-scaled models in the collaborative learning scenario, and propose a new lightweight framework for split learning based on mask, masked Split Learning (MaskSL). We further ensure its security by differential privacy. Besides, we model the computation and communication overheads of several collaborative learning approaches by deduction to illustrate advantages of our scheme. Finally, we design and conduct a series of experiments on real-world datasets, e.g., in face recognition and medical image classification tasks, to demonstrate the performance of MaskSL.

关键词： Computational modeling Training Federated learning Privacy Data models Transformers Task analysis Split learning self pre-training differential privacy masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Mixup Feature: A Pretext Task Self-Supervised Learning Method for Enhanced Visual Feature Learning

引用

IEEE ACCESS 2023年 11卷 82400-82409页

作者： Xu, Jiashu Stirenko, Sergii Natl Tech Univ Ukraine Comp Engn Dept Igor Sikorsky Kyiv Polytech Inst UA-03056 Kiev Ukraine

Self-supervised learning has emerged as an increasingly popular research topic within the field of computer vision. In this study, we propose a novel self-supervised learning approach based on Mixup features as pretext tasks. The proposed method aims to learn visual representations by predicting the MixupFeature of a masked image, which serves as a proxy for higher-level semantic information. Specifically, we investigate the efficacy of Mixup features as the prediction target for self-supervised learning. By setting the hyperparameter ? through Mixup operations, pairwise combinations of Sobel edge feature maps, HOG feature maps, and LBP feature maps are created. We employ the vision transformer as the backbone network, drawing inspiration from masked autoencoders (MAE). We evaluate the proposed method on three benchmark datasets, namely Cifar-10, Cifar-100, and STL-10, and compare it with other state-ofthe-art self-supervised learning approaches. The experiments demonstrate that mixed HOG-Sobel feature maps after Mixup achieve the best results in fine-tuning experiments on Cifar-10 and STL-10. Furthermore, compared to contrastive learning-based self-supervised learning methods, our approach proves to be more efficient, with shorter training durations and no reliance on data augmentation. When compared to generative self-supervised learning approaches based on MAE, the average performance improvement is 0.4%. Overall, the proposed self-supervised learning method based on Mixup features offers a promising direction for future research in the computer vision domain and has the potential to enhance performance across various downstream tasks. Our code will be published in GitHub.

关键词： Computer vision mixup feature self-supervised learning masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Rethinking Polyp Segmentation from An Out-ofdistribution Perspective

引用

Machine Intelligence Research 2024年第4期21卷 631-639页

作者： Ge-Peng Ji Jing Zhang Dylan Campbell Huan Xiong Nick Barnes Australian National University Canberra 8105Australia Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi 999041UAE

Unlike existing fully-supervised approaches,we rethink colorectal polyp segmentation from an out-of-distribution perspective with a simple but effective self-supervised learning *** leverage the ability of masked autoencoders-self-supervised vision transformers trained on a reconstruction task-to learn in-distribution representations,here,the distribution of healthy colon *** then perform out-of-distribution reconstruction and inference,with feature space standardisation to align the latent distribution of the diverse abnormal samples with the statistics of the healthy *** generate per-pixel anomaly scores for each image by calculating the difference between the input and reconstructed images and use this signal for out-of-distribution(i.e.,polyp)*** results on six benchmarks show that our model has excellent segmentation performance and generalises across *** code is publicly available at https://***/GewelsJI/Polyp-OOD.

关键词： Polyp segmentation anomaly segmentation out-of-distribution segmentation masked autoencoder abdomen.

来源：评论

学校读者我要写书评

暂无评论

masked Embedding Modeling With Rapid Domain Adjustment for Few-Shot Image Classification

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 4907-4920页

作者： Walsh, Reece Osman, Islam Shehata, Mohamed S. Univ British Columbia Dept Comp Sci Kelowna BC V6T 1Z4 Canada

In few-shot classification, performing well on a testing dataset is a challenging task due to the restricted amount of labelled data available and the unknown distribution. Many previously proposed techniques rely on prototypical representations of the support set in order to classify a query set. Although this approach works well with a large, in-domain support set, accuracy suffers when transitioning to an out-of-domain setting, especially when using small support sets. To address out-of-domain performance degradation with small support sets, we propose masked Embedding Modeling for Few-Shot Learning (MEM-FS), a novel, self-supervised, generative technique that reinforces few-shot-classification accuracy for a prototypical backbone model. MEM-FS leverages the data completion capabilities of a masked autoencoder to expand a given embedded support set. To further increase out-of-domain performance, we also introduce Rapid Domain Adjustment (RDA), a novel, self-supervised process for quickly conditioning MEM-FS to a new domain. We show that masked support embeddings generated by MEM-FS+RDA can significantly improve backbone performance on both out-of-domain and in-domain datasets. Our experiments demonstrate that applying the proposed technique to an inductive classifier achieves state-of-the-art performance on mini-imagenet, the CVPR L2ID Classification Challenge, and a newly proposed dataset, IKEA-FS. We provide code for this work at https://***/Brikwerk/MEM-FS

关键词： Few-shot classification self-supervised generative masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multimodal Feature-Guided Pretraining for RGB-T Perception

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 16041-16050页

作者： Ouyang, Junlin Jin, Pengcheng Wang, Qingwang Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Peoples R China

Wide-range multiscale object detection for multispectral scene perception from a drone perspective is challenging. Previous RGB-T perception methods directly use backbone pretrained on RGB for thermal infrared feature extraction, leading to unexpected domain shift. We propose a novel multimodal feature-guided masked reconstruction pretraining method, named M2FP, aimed at learning transferable representations for drone-based RGB-T environmental perception tasks without domain bias. This article includes two key innovations as follows. 1) We design a cross-modal feature interaction module in M2FP, which encourages modality-specific backbones to actively learn cross-modal feature representations and avoid modality bias issues. 2) We design a global-aware feature interaction and fusion module suitable for various downstream tasks, which enhances the model's environmental perception from a global perspective in wide-range drone-based scenes. We fine-tune M2FP on the drone-based object detection dataset (DroneVehicle) and semantic segmentation dataset (Kust4K). On these two tasks, compared to the second-best methods, M2FP achieves state-of-the-art performance, with an improvement of 1.8% in mean average precision and 0.9% in mean intersection over union, respectively.

关键词： Feature extraction Task analysis Image reconstruction Object detection Semantic segmentation Pipelines Visualization masked autoencoder multimodal object detection semantic segmentation unmanned aerial vehicle (UAV) remote sensing

来源：评论

学校读者我要写书评

暂无评论

ViT-UperNet: a hybrid vision transformer with unified-perceptual-parsing network for medical image segmentation

引用

COMPLEX & INTELLIGENT SYSTEMS 2024年第3期10卷 3819-3831页

作者： Ruiping, Yang Kun, Liu Shaohua, Xu Jian, Yin Zhen, Zhang Shandong Univ Sci & Technol Coll Econ & Management Qianwangang Rd Qingdao 266590 Shandong Peoples R China Shandong Univ Sci & Technol Coll Comp Sci & Engn Qianwangang Rd Qingdao 266590 Shandong Peoples R China

The existing image semantic segmentation models have low accuracy in detecting tiny targets or multi-targets at overlapping regions. This work proposes a hybrid vision transformer with unified-perceptual-parsing network (ViT-UperNet) for medical image segmentation. A self-attention mechanism is embedded in a vision transformer to extract multi-level features. The image features are extracted hierarchically from low to high dimensions using 4 groups of Transformer blocks with different numbers. Then, it uses a unified-perceptual-parsing network based on a feature pyramid network (FPN) and a pyramid pooling module (PPM) for the fusion of multi-scale contextual features and semantic segmentation. FPN can naturally use hierarchical features, and generate strong semantic information on all scales. PPM can better use the global prior knowledge to understand complex scenes, and extract features with global context information to improve segmentation results. In the training process, a scalable self-supervised learner named masked autoencoder is used for pre-training, which strengthens the visual representation ability and improves the efficiency of the feature learning. Experiments are conducted on cardiac magnetic resonance image segmentation where the left and right atrium and ventricle are selected for segmentation. The pixels accuracy is 93.85%, the Dice coefficient is 92.61% and Hausdorff distance is 11.16, which are improved compared with the other methods. The results show the superiority of Vit-UperNet in medical images segmentation, especially for the low-recognition and serious-occlusion targets.

关键词： Medical image segmentation Deep learning Self-attention mechanism masked autoencoder

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：