检索结果-内蒙古大学图书馆

Proceedings of the 2023 International Conference on Hardware/Software Codesign and System Synthesis

作者： Qiaochu Liang Lei Gong Chao Wang Xuehai Zhou Xi Li University of Science and Technology of China Hefei Jiangsu China University of Science and Technology of China Hefei Anhui China

ISBN: (纸本)9798400702891

Predictor-based Neural Architecture Search (NAS) offers a promising solution for enhancing the efficiency of traditional NAS methods. However, it is non-trivial to train the predictor with limited architecture evaluations for efficient NAS. In this paper, we propose a self-supervised transformer-based model that leverages unlabeled data to learn meaningful representations of neural architectures. After pre-training with a masked autoencoder, the predictor can adapt to various performance metrics estimation with limited supervised data. Experimental results demonstrate that our predictor requires less labeled data and achieves superior performance compared to existing predictors.

关键词： neural architecture search masked autoencoder transformer

来源：评论

学校读者我要写书评

暂无评论

MaeFuse: Transferring Omni Features With Pretrained masked autoencoders for Infrared and Visible Image Fusion via Guided Training

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2025年 34卷 1340-1353页

作者： Li, Jiayang Jiang, Junjun Liang, Pengwei Ma, Jiayi Nie, Liqiang Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Peoples R China Wuhan Univ Elect Informat Sch Wuhan 430072 Peoples R China Harbin Inst Technol Shenzhen Sch Comp Sci & Technol Shenzhen 518055 Peoples R China

In this paper, we introduce MaeFuse, a novel autoencoder model designed for Infrared and Visible Image Fusion (IVIF). The existing approaches for image fusion often rely on training combined with downstream tasks to obtain high-level visual information, which is effective in emphasizing target objects and delivering impressive results in visual quality and task-specific applications. Instead of being driven by downstream tasks, our model called MaeFuse utilizes a pretrained encoder from masked autoencoders (MAE), which facilities the omni features extraction for low-level reconstruction and high-level vision tasks, to obtain perception friendly features with a low cost. In order to eliminate the domain gap of different modal features and the block effect caused by the MAE encoder, we further develop a guided training strategy. This strategy is meticulously crafted to ensure that the fusion layer seamlessly adjusts to the feature space of the encoder, gradually enhancing the fusion performance. The proposed method can facilitate the comprehensive integration of feature vectors from both infrared and visible modalities, thus preserving the rich details inherent in each modal. MaeFuse not only introduces a novel perspective in the realm of fusion techniques but also stands out with impressive performance across various public datasets. The code is available at https://***/Henry-Lee-real/MaeFuse.

关键词： Image fusion vision transformer vision transformer masked autoencoder masked autoencoder guided training guided training

来源：评论

学校读者我要写书评

暂无评论

Mask autoencoder for enhanced image reconstruction with position coding offset and combined masking

引用

VISUAL COMPUTER 2025年 1-15页

作者： Wang, Yuenan Wang, Hua Zhang, Fan Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai 264005 Shandong Peoples R China Ludong Univ Sch Informat & Elect Engn Yantai 264025 Shandong Peoples R China Shandong Technol & Business Univ Sch Comp Sci & Technol Yantai 264005 Shandong Peoples R China Shandong Technol & Business Univ Shandong Future Intelligent Financial Engn Lab Yantai 264005 Shandong Peoples R China

Existing masked image modeling (MIM) methods mainly fill and enhance images by modeling and filling masked areas. These techniques usually borrow principles from computer graphics, where similar methods are used to synthesize missing parts of images or meshes. However, current MIM methods still have problems such as incomplete capture of local information and failure to capture dynamic information. To address the above situation, we propose a multi-mask autoencoder (M-MAE). M-MAE borrows the smooth transition technology from computer graphics, combines patch masking and random masking, and enhances the stability of the model by optimizing the processing of masked areas during training. In addition, we introduce a scaling layer (LScale) to improve training dynamics, similar to the scaling and distortion transformations used in graphics to adapt to different spatial distributions. To further improve the accuracy of the model in capturing spatial relationships, we propose a position encoding offset method that can generate more spatially aware encodings, thereby effectively enhancing the spatial expression ability of the model. Comparative experiments show that M-MAE can achieve an Acc1 of 84.5 on the ImageNet-1K dataset, an Acc1 of 58.2 on the Places365 dataset, and an mIoU of 49.4 on the ADE20K dataset. From the experimental results, it can be seen that our innovation improves the performance of the model in multiple visual tasks and provides a tighter integration between visual and graphics methods. Code is released at (https://***/zoomba35/mmae).

关键词： masked image modeling masked autoencoder Vision transformer Position encoding Computer graphics

来源：评论

学校读者我要写书评

暂无评论

Analyzing different phenotypic methods of soybean leaves under the high temperature stress with near-infrared spectroscopy, microscopic Image, and multispectral image

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2025年 234卷

作者： Deng, Youhui Yang, Weizhi Li, Jiajia Zhang, Xiaodan Rao, Yuan Chen, Haoran Xiong, Jianghui Chen, Xi Wang, Xiaobo Jin, Xiu Anhui Agr Univ Sch Informat & Artificial Intelligence Hefei 230001 Peoples R China Anhui Agr Univ Key Lab Agr Sensors Minist Agr & Rural Affairs Hefei 230001 Peoples R China Anhui Agr Univ Sch Agron Hefei 230001 Peoples R China

High temperature stress (HT) plays an important role in soybean selection and breeding, it can cause changes in soybean physiological, biochemical and morphological traits, and directly affect the growth and yield of soybean plants. Among these changes, soybean leaves are particularly sensitive to HT during growth and development. It is important to establish a non-destructive method to distinguish the phenotypic differences between soybean plants under HT and control (CK). In this study, data from two years of soybean field trials were used. In the first year, phenotypic information was collected by near-infrared spectroscopy (NIR), microscopic images, and further difference analysis and classification modelling experiments were conducted. In the second year, multispectral image data were collected and analyzed by Soybean high temperature mask autoencoder (SHT_MAE). The SHT_MAE model with a 75% masking ratio achieved an accuracy of 89.16% and an F1-score of 89.18%. Compared with one-dimensional near-infrared and two-dimensional microscopic image fusion models, the classification accuracy of HT and CK is improved by 2.68%. The accuracy of SHT_MAE multispectral model was improved by 16.84% and 6.88%, respectively, compared with models using only NIR or microscopic images. Both spectral and imaging methods effectively distinguish the phenotypic differences between HT and CK soybean leaves, with the multispectral approach based on the SHT_MAE model demonstrating a clear advantage. This study realized the effective distinction of soybean leaves under HT and CK. It provides theoretical support for HT intelligent breeding (using artificial intelligence and data analysis to optimize breeding decisions) and high temperature grade prediction.

关键词： Soybean leaves High-temperature stress Phenotype Deep learning model masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Calibration transfer of sugar content prediction models for agricultural products via NIR spectral augmentation and reconstruction architecture

引用

BIOSYSTEMS ENGINEERING 2025年 253卷

作者： Zhao, Anyi Fu, Xiaping Wu, Jingqian Zhang, Jianyi Zhejiang Sci Tech Univ Sch Mat Sci & Engn Hangzhou 310018 Zhejiang Peoples R China Zhejiang Sci Tech Univ Sch Mech Engn Hangzhou 310018 Zhejiang Peoples R China

Rapid non-destructive determination of sugar content in agricultural products such as pear and sugarcane is critical for optimising harvest timing and enhancing market competitiveness. However, near infrared spectroscopy-based prediction models suffer from degraded generalisation performance during cross-year or cross-device transfers, primarily due to insufficient sample sizes and spectral variability, which significantly hinders their large-scale deployment in agricultural engineering. To address these challenges, this study proposes a novel spectral masked autoencoder generative adversarial network (SMAEGAN), which integrates adversarial training with a masked autoencoder strategy to synthesise high-fidelity spectral data with enhanced crossdomain generalisation capabilities, thereby effectively mitigating data scarcity in few-shot transfer learning scenarios. Furthermore, a pyramid associative self-attention spectral transformer (PASASpTr) was introduced that hierarchically extracts multi-scale spectral features through an innovative pyramid architecture, enabling the synergistic capture of both local band-specific variations and global patterns. Comprehensive experimental evaluations demonstrate that PASASpTr significantly outperforms traditional convolutional neural networks in sugarcane sugar content prediction, achieving a root mean square error (RMSE) of 3.40, a coefficient of determination (R2) of 0.93, and a parameter size of 0.94 M. When combined with SMAEGAN-augmented reconstructed spectra for transfer learning, an average RMSE reduction of 44.68 % was achieved in the sugarcane dataset collected across different devices, and an average RMSE reduction of 40.65 % was achieved in the pear dataset collected across different years and production lines. This methodological architecture significantly reduces the reliance on target-domain annotated samples, while offering a lightweight and scalable solution for predicting sugar content across a wide range of ag

关键词： Sugar content Generative adversarial network masked autoencoder Pyramid associative self-attention Data augmentation Near-infrared spectra reconstruction

来源：评论

学校读者我要写书评

暂无评论

LPRnet: A Self-Supervised Registration Network for LiDAR and Photogrammetric Point Clouds

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Wang, Chen Gu, Yanfeng Li, Xian Harbin Inst Technol Sch Elect & Informat Engn Harbin 150001 Peoples R China

LiDAR and photogrammetry are active and passive remote sensing techniques for point cloud acquisition, respectively, offering complementary advantages and heterogeneous. Due to the fundamental differences in sensing mechanisms, spatial distributions, and coordinate systems, their point clouds exhibit significant discrepancies in density, precision, noise, and overlap. Coupled with the lack of ground truth for large-scale scenes, integrating the heterogeneous point clouds is a highly challenging task. This article proposes a self-supervised registration network based on a masked autoencoder, focusing on heterogeneous LiDAR and photogrammetric point clouds. At its core, the method introduces a multiscale masked training strategy to extract robust features from heterogeneous point clouds under self-supervision. To further enhance registration performance, a rotation-translation embedding module is designed to effectively capture the key features essential for accurate rigid transformations. Building upon robust representations, a transformer-based architecture seamlessly integrates local and global features, fostering precise alignment across diverse point cloud datasets. The proposed method demonstrates strong feature extraction capabilities for both LiDAR and photogrammetric point clouds, addressing the challenges of acquiring ground truth at the scene level. Experiments conducted on two real-world datasets validate the effectiveness of the proposed method in solving heterogeneous point cloud registration problems.

关键词： Point cloud compression Laser radar Feature extraction Three-dimensional displays Training Surface emitting lasers Photogrammetry Image reconstruction autoencoders Accuracy LiDAR point cloud masked autoencoder photogrammetric point cloud registration self-supervised

来源：评论

学校读者我要写书评

暂无评论

A Weakly Supervised and Self-Supervised Learning Approach for Semantic Segmentation of Land Cover in Satellite Images with National Forest Inventory Data

引用

REMOTE SENSING 2025年第4期17卷 711-711页

作者： Moraes, Daniel Campagnolo, Manuel L. Caetano, Mario Univ Nova Lisboa NOVA Informat Management Sch NOVA IMS Campus Campolide P-1070312 Lisbon Portugal Direcao Geral Terr Rua Artilharia 107 P-1099052 Lisbon Portugal Univ Lisbon Forest Res Ctr CEF Sch Agr Associate Lab TERRA P-1349017 Tapada Da Ajuda Lisbon Portugal

National Forest Inventories (NFIs) provide valuable land cover (LC) information but often lack spatial continuity and an adequate update frequency. Satellite-based remote sensing offers a viable alternative, employing machine learning to extract thematic data. State-of-the-art methods such as convolutional neural networks rely on fully pixel-level annotated images, which are difficult to obtain. Although reference LC datasets have been widely used to derive annotations, NFIs consist of point-based data, providing only sparse annotations. Weakly supervised and self-supervised learning approaches help address this issue by reducing dependence on fully annotated images and leveraging unlabeled data. However, their potential for large-scale LC mapping needs further investigation. This study explored the use of NFI data with deep learning and weakly supervised and self-supervised methods. Using Sentinel-2 images and the Portuguese NFI, which covers other LC types beyond forest, as sparse labels, we performed weakly supervised semantic segmentation with a convolutional neural network to create an updated and spatially continuous national LC map. Additionally, we investigated the potential of self-supervised learning by pretraining a masked autoencoder on 65,000 Sentinel-2 image chips and then fine-tuning the model with NFI-derived sparse labels. The weakly supervised baseline achieved a validation accuracy of 69.60%, surpassing Random Forest (67.90%). The self-supervised model achieved 71.29%, performing on par with the baseline using half the training data. The results demonstrated that integrating both learning approaches enabled successful countrywide LC mapping with limited training data.

关键词： land cover deep learning convolutional neural networks masked autoencoder national forest inventory sentinel-2

来源：评论

学校读者我要写书评

暂无评论

SkelETT-Skeleton-to-Emotion Transfer Transformer

引用

IEEE ACCESS 2025年 13卷 23344-23358页

作者： Paiva, Pedro Victor Vieira Ramos, Josue Junior Guimaraes Gavrilova, Marina de Carvalho, Marco Antonio Garcia Univ Estadual Campinas Sch Technol BR-13484332 Limeira Brazil Univ Calgary Dept Comp Sci Calgary AB T2N 1N4 Canada Renato Archer IT Ctr BR-13069901 Campinas Brazil

Emotion recognition plays an essential role in human-computer interaction, spanning diverse domains from human-robot communication and virtual reality to mental health assessment and affective computing. Traditionally, this field has heavily relied on visual and auditory cues, such as facial expressions and speech analysis. However, these modalities alone may not comprehensively capture the full spectrum of human emotion and suffer limitations due to noise or occlusion. Human skeletons, derived from depth sensors or pose estimation algorithms, offer an alternative for facial expression, including valuable spatial and temporal cues. In this paper, we introduce a novel approach to emotion recognition by pre-training a transformer model on a large dataset of unsupervised human skeleton representations and subsequently fine-tuning it for emotion classification. By exposing the model to an extensive corpus of unlabeled human skeleton data, we can effectively learn to represent complex spatial and temporal dependencies inherent in body movements. Following this foundational knowledge acquisition, the model undergoes fine-tuning on a smaller, labeled dataset tailored for emotion classification tasks. We introduce SkelETT, an encoder-only transformer architecture for body emotion recognition. Comprising a series of encoder layers, SkelETT patches 2D body pose representations, it also includes multi-head self-attention mechanisms and position-wise feed-forward networks, providing a powerful framework for extracting hierarchical features from sequential body pose data. We propose and evaluate the impact of different fine-tuning strategies on pose data using the MPOSE action recognition dataset as a pre-training source. Transfer performance is measured on the BoLD body emotion recognition dataset. Compared to the state-of-the-art, we report significant gains in accuracy (approximate to 34% higher), training time (approximate to 50% less), and model complexity reduction (approx

关键词： Emotion recognition Transformers Skeleton Adaptation models Accuracy Computational modeling Transfer learning Training Solid modeling Data models Attention-based design body emotion recognition gait analysis masked autoencoder affective computing

来源：评论

学校读者我要写书评

暂无评论

VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification 15th

VIS-MAE: An Efficient Self-supervised Learning Approach on M...

引用

15th International Workshop on Machine Learning in Medical Imaging

作者： Liu, Zelong Tieu, Andrew Patel, Nikhil Soultanidis, George Deyer, Louisa Wang, Ying Huver, Sean Zhou, Alexander Mei, Yunhao Fayad, Zahi A. Deyer, Timothy Mei, Xueyan Icahn Sch Med Mt Sinai BioMed Engn & Imaging Inst New York NY 10029 USA Univ Oklahoma Dept Math Norman OK 73019 USA NVIDIA Santa Clara CA USA Erasmus Univ Rotterdam Netherlands East River Med Imaging New York NY USA Cornell Med Dept Radiol New York NY USA Icahn Sch Med Mt Sinai Windreich Dept Artificial Intelligence & Human Hl New York NY 10029 USA

ISBN: (纸本)9783031732928;9783031732904

Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of generalizability, and the necessity to incorporate multi-modal data effectively. A foundation model, which is a large-scale pre-trained AI model, offers a versatile base that can be adapted to a variety of specific tasks and contexts. Here, we present VIsualization and Segmentation masked autoencoder (VIS-MAE), novel model weights specifically designed for medical imaging. Specifically, VIS-MAE is trained on a dataset of 2.5 million unlabeled images from various modalities (CT, MR, PET, X-rays, and ultrasound), using self-supervised learning techniques. It is then adapted to classification and segmentation tasks using explicit labels. VIS-MAE has high label efficiency, outperforming several benchmark models in both in-domain and out-of-domain applications. In addition, VIS-MAE has improved label efficiency as it can achieve similar performance to other models with a reduced amount of labeled training data (50% or 80%) compared to other pre-trained weights. VIS-MAE represents a significant advancement in medical imaging AI, offering a generalizable and robust solution for improving segmentation and classification tasks while reducing the data annotation workload. The source code of this work is available at https://***/lzl199704/VIS-MAE.

关键词： Self-supervised Learning masked autoencoder Medical Image Segmentation and Classification Label efficiency

来源：评论

学校读者我要写书评

暂无评论

masked autoencoders as Single Object Tracking Learners

引用

Computers, Materials & Continua 2024年第7期80卷 1105-1122页

作者： Chunjuan Bo XinChen Junxing Zhang School of Information and Communication Engineering Dalian Minzu UniversityDalian116600China School of Information and Communication Engineering Dalian University of TechnologyDalian116024China

Significant advancements have beenwitnessed in visual tracking applications leveragingViT in recent years,mainly due to the formidablemodeling capabilities of Vision Transformer(ViT).However,the strong performance of such trackers heavily relies on ViT models pretrained for long periods,limitingmore flexible model designs for tracking *** address this issue,we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders,called *** pretraining,we employ two shared-parameter ViTs,serving as the appearance encoder and motion encoder,*** appearance encoder encodes randomly masked image data,while the motion encoder encodes randomly masked pairs of video ***,an appearance decoder and a motion decoder separately reconstruct the original image data and video frame data at the pixel *** this way,ViT learns to understand both the appearance of images and the motion between video frames *** results demonstrate that ViT-Base and ViT-Large models,pretrained with TrackMAE and combined with a simple tracking head,achieve state-of-the-art(SOTA)performance without additional ***,compared to the currently popular MAE pretraining methods,TrackMAE consumes only 1/5 of the training time,which will facilitate the customization of diverse models for *** instance,we additionally customize a lightweight ViT-XS,which achieves SOTA efficient tracking performance.

关键词： Visual object tracking vision transformer masked autoencoder visual representation learning

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：