CNN Attention Enhanced ViT Network for Occluded Person Re-Identification

Wang, Jing; Li, Peitong; Zhao, Rongfeng; Zhou, Ri-Gui; Han, Yanling

doi:10.3390/app13063707

Cited by 7 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It balances high classification accuracy with minimal parameters and latency. Wang et al [44] developed RepViT, a pure CNN architecture incorporating lightweight ViT [45] principles to refine traditional lightweight CNNs, achieving low latency and high accuracy. EfficientViT by Liu et al [46] improves memory and computational efficiency with a sandwich layout and cascaded group attention while preserving accuracy.…”

Section: B Backbone Network For Object Detectionmentioning

confidence: 99%

SatDetX-YOLO: A More Accurate Method for Vehicle Target Detection in Satellite Remote Sensing Imagery

Zhao,

Guo,

Shao

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Satellite remote sensing technology significantly contributes to intelligent transportation by optimizing traffic planning via global perspectives and rich data, enhancing traffic efficiency and reducing environmental impact. However, current target detection models frequently exhibit low accuracy in vehicle detection tasks due to complex background interference in satellite imageries and a need for critical semantic information. To improve vehicle target detection accuracy, this study introduces SatDetX-YOLO, a vehicle detection model for satellite remote sensing images based on YOLOv8. The model involves reconstructing the backbone network with FasterNet for enhanced feature extraction, a redesigned decoupled head for improved computational efficiency and complex data processing, and incorporating the Deformable Attention Module (DAM) to increase sensitivity to small targets and feature correlation capture. Employing the Maximum Probabilistic Distance IoU (MPDIoU) loss function enhances adaptability and generalization to diverse vehicle targets. Experimental results demonstrate that under comparable FPS, SatDetX-YOLO's Precision (P), Recall (R), and Mean Average Precision (mAP) improved by 3.5%, 3.3%, and 3.2%, respectively. Despite a minor reduction in FPS, the model significantly enhances detection accuracy, striking a balance between accuracy and speed.

show abstract

Section: B Backbone Network For Object Detectionmentioning

confidence: 99%

SatDetX-YOLO: A More Accurate Method for Vehicle Target Detection in Satellite Remote Sensing Imagery

Zhao,

Guo,

Shao

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Meanwhile, MobileFormer devised an architecture that parallels MobileNet and converters via a two-way bridge [43]. Integrating these efficient architecture choices for lightweight ViTs, Wang et al [59] pro-gressively enhanced the mobility of standard lightweight CNNs, notably MobileNetV3, culminating in the development of RepViT. Despite adopting a MetaFormer structure [60], RepViT is solely composed of convolutional layers, showcasing superior performance and efficiency compared to most advanced lightweight ViTs across various computer vision tasks.…”

Section: Network Lightweightmentioning

confidence: 99%

Lightweight Super-Resolution Reconstruction Vision Transformers of Remote Sensing Image Based on Structural Re-Parameterization

Bian,

Liu,

Chen

2024

Applied Sciences

View full text Add to dashboard Cite

In recent times, remote sensing image super-resolution reconstruction technology based on deep learning has experienced rapid development. However, most algorithms in this domain concentrate solely on enhancing the super-resolution network’s performance while neglecting the equally crucial aspect of inference speed. In this study, we propose a method for lightweight super-resolution reconstruction of remote sensing images, termed SRRepViT. This approach reduces model parameters and floating-point operations during inference through parameter equivalent transformation. Using the RSSOD remote sensing dataset as our benchmark dataset, we compared the reconstruction performance, inference time, and model size of SRRepViT with other classical methods. Compared to the lightweight model ECBSR, SRRepViT exhibits slightly improved reconstruction performance while reducing inference time by 16% and model parameters by 34%, respectively. Moreover, compared to other classical super-resolution reconstruction methods, the SRRepViT model achieves similar reconstruction performance while reducing model parameters by 98% and increasing inference speed by 90% for a single remote sensing image.

show abstract

“…In the automated defect detection method based on artificial intelligence technology, the ability of the computer to automatically learn and recognize various types of flaws is enabled by the use of deep learning technology and an enormous quantity of data, thus realizing efficient and accurate automated detection. In supervised learning methods [3], to train the model using supervised learning techniques, a lot of labeled data is needed, but the cost of such data acquisition and labeling is high, which is not conducive to practical application. Whereas, in self-supervised learning methods [4], only a large amount of unlabeled data needs to be utilized for learning, which reduces the labeling cost.…”

Section: Introductionmentioning

confidence: 99%

Self-supervised fabric defect detection model combined with transformer

Xie,

Zhao

2024

Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023)

View full text Add to dashboard Cite

In industrial manufacturing, defect detection is essential. Since the 2020's ViT (vision transformer) hit the scene, ViT has been increasingly used for defect detection tasks in the vision domain. The advantage of ViT over convolutional neural networks (CNNs) is its ability to capture global remote dependencies to learn better features. In addition to this, contrast learning based on self-supervised methods has been well used in defect detection tasks. In this study, we suggest a strategy for detecting fabric defects that combines transformer and contrast learning. First, we propose a new backbone network CViT (convolutional vision transformer), which is improved relative to ViT by adding a convolutional attention module to the ordinary transformer block structure while using depthwise separable convolution instead of linear projection to obtain q, k, and v for attention computation. Second, to compensate for the potential instability of CViT, instead of the 16 × 16 big convolutions used in the ViT, we use several stacked 3 × 3 tiny convolutions to divide each enhanced sample into a series of patches. Third, we incorporate conditional position encoding(CPE) and explore the impact of different position encodings on model performance. Finally, the effectiveness of our model is demonstrated on three classical public datasets for fabric fault detection.

show abstract

CNN Attention Enhanced ViT Network for Occluded Person Re-Identification

Cited by 7 publications

References 40 publications

SatDetX-YOLO: A More Accurate Method for Vehicle Target Detection in Satellite Remote Sensing Imagery

SatDetX-YOLO: A More Accurate Method for Vehicle Target Detection in Satellite Remote Sensing Imagery

Lightweight Super-Resolution Reconstruction Vision Transformers of Remote Sensing Image Based on Structural Re-Parameterization

Self-supervised fabric defect detection model combined with transformer

Contact Info

Product

Resources

About