Online Convolutional Reparameterization

Hu, Mu; Feng, Junyi; Hua, Jiashen; Lai, Baisheng; Huang, Jianqiang; Gong, Xiaojin; Hua, Xian-Sheng

doi:10.1109/cvpr52688.2022.00065

Cited by 33 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technique enables efficient training and deployment of deep learning models in scenarios with limited computational resources by using constant parameter transformations to reduce the storage and computational resources of the model through simplification of the network structure. As shown in Figure 5 , the earlier RepVGG model uses a simple architecture consisting of stacked 3*3 Conv and ReLU to achieve structural decoupling during training and inference, and uses a multi-branch structure during training, and then uses reparameterization to equivalently transform the multi-branch architecture to a VGG single-way architecture with stacked 3*3 convolutional layers after training was completed, using this structured reparameterization method to enable RepVGG to achieve ImageNet to achieve more than 80% accuracy and run several times faster ( Transactions of the Chinese Society of Agricultural Engineering et al., 2021 ; Hu et al., 2022 ).…”

Section: Tests and Methodsmentioning

confidence: 99%

Construction and verification of machine vision algorithm model based on apple leaf disease images

Ang,

Han,

Yuepeng

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Apple leaf diseases without timely control will affect fruit quality and yield, intelligent detection of apple leaf diseases was especially important. So this paper mainly focuses on apple leaf disease detection problem, proposes a machine vision algorithm model for fast apple leaf disease detection called LALNet (High-speed apple leaf network). First, an efficient sacked module for apple leaf detection, known as EALD (efficient apple leaf detection stacking module), was designed by utilizing the multi-branch structure and depth-separable modules. In the backbone network of LALNet, (High-speed apple leaf network) four layers of EALD modules were superimposed and an SE(Squeeze-and-Excitation) module was added in the last layer of the model to improve the attention of the model to important features. A structural reparameterization technique was used to combine the outputs of two layers of deeply separable convolutions in branch during the inference phase to improve the model’s operational speed. The results show that in the test set, the detection accuracy of the model was 96.07%. The total precision was 95.79%, the total recall was 96.05%, the total F1 was 96.06%, the model size was 6.61 MB, and the detection speed of a single image was 6.68 ms. Therefore, the model ensures both high detection accuracy and fast execution speed, making it suitable for deployment on embedded devices. It supports precision spraying for the prevention and control of apple leaf disease.

show abstract

Section: Tests and Methodsmentioning

confidence: 99%

Construction and verification of machine vision algorithm model based on apple leaf disease images

Ang,

Han,

Yuepeng

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…Model Re-Parameterization. Model re-parameterization is a technique for improving the efficiency and performance of networks by merging multiple computational modules into a fully equivalent module at the inference stage [55] denotes the Hadamard product, ⊗ denotes the matrix product, and denotes the matrix addition.…”

Section: Training Optimizationmentioning

confidence: 99%

“…Model Re-Parameterization. Model re-parameterization is a technique for improving the efficiency and performance of networks by merging multiple computational modules into a fully equivalent module at the inference stage [55] Dynamic Label Assignment. If we follow the commonly hand-crafted label assignment strategy to assign the optimal anchor to each ground truth, there may be multiple ground truths corresponding to the same anchor, which has a significantly negative impact on network training.…”

Section: Training Optimizationmentioning

confidence: 99%

Multi-Task Visual Perception for Object Detection and Semantic Segmentation in Intelligent Driving

Zhan,

Liu,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

With the rapid development of intelligent driving vehicles, multi-task visual perception based on deep learning emerges as a key technological pathway toward safe vehicle navigation in real traffic scenarios. However, due to the high-precision and high-efficiency requirements of intelligent driving vehicles in practical driving environments, multi-task visual perception remains a challenging task. Existing methods typically adopt effective multi-task learning networks to concurrently handle multiple tasks. Despite the fact that they obtain remarkable achievements, better performance can be achieved through tackling existing problems like underutilized high-resolution features and underexploited non-local contextual dependencies. In this work, we propose YOLOPv3, an efficient anchor-based multi-task visual perception network capable of handling traffic object detection, drivable area segmentation, and lane detection simultaneously. Compared to prior works, we make essential improvements. On the one hand, we propose architecture enhancements that can utilize multi-scale high-resolution features and non-local contextual dependencies for improving network performance. On the other hand, we propose optimization improvements aiming at enhancing network training, enabling our YOLOPv3 to achieve optimal performance via straightforward end-to-end training. The experimental results on the BDD100K dataset demonstrate that YOLOPv3 sets a new state of the art (SOTA): 96.9% recall and 84.3% mAP50 in traffic object detection, 93.2% mIoU in drivable area segmentation, and 88.3% accuracy and 28.0% IoU in lane detection. In addition, YOLOPv3 maintains competitive inference speed against the lightweight YOLOP. Thus, YOLOPv3 stands as a robust solution for handling multi-task visual perception problems. The code and trained models have been released on GitHub.

show abstract

“…To solve the above problems, we propose a lightweight ship detection method based on Swin-YOLOFormer. YOLOv7 14 is the latest detection model in the YOLO series model, introduces the reparameterized 15 module into the network architecture, reduces the calculation of the model, and introduces the label allocation strategy and ELAN. 16 Finally, YOLOv7 proposes the training method of the auxiliary header to increase the training cost and improve the accuracy without affecting the time of reasoning, because the auxiliary head will only appear in the training process.…”

Section: Introductionmentioning

confidence: 99%

Lightweight ship detection method based on Swin-YOLOFormer

Cen,

Chen,

Liu

et al. 2024

J. Electron. Imag.

View full text Add to dashboard Cite

Deep learning models have achieved great success in the field of ship detection, but these models often require a large amount of computing and storage resources, and are not suitable for some resource-constrained situations. To solve the above problems, we propose a lightweight Swin-YOLOFormer ship detection method. First, in terms of the backbone network, the Swin transformer lightweight model is introduced to reduce the redundancy parameters of the backbone network. Second, in the feature fusion network, an improved ghost-efficient long-range attention network-hierarchy module is proposed to extract features and reduce the burden of model parameters. Finally, in order to prevent feature loss, an improved SPPCPSC module is proposed to enhance the feature of receptive field. Through experimental verification, compared with the YOLOv7 benchmark model, the number of proposed model parameters was reduced by 66.05% to 13.501 M, which not only accelerated the model training speed but also reached 97.81% accuracy. The results show that the proposed method achieves model lightweight and maintain high precision.

show abstract

Online Convolutional Reparameterization

Cited by 33 publications

References 12 publications

Construction and verification of machine vision algorithm model based on apple leaf disease images

Construction and verification of machine vision algorithm model based on apple leaf disease images

Multi-Task Visual Perception for Object Detection and Semantic Segmentation in Intelligent Driving

Lightweight ship detection method based on Swin-YOLOFormer

Contact Info

Product

Resources

About