Conv2NeXt: Reconsidering Conv NeXt Network Design for Image Recognition

Feng, Jianwei; Tan, Hengliang; Li, Wangwang; Xie, Ming

doi:10.1109/cait56099.2022.10072172

Cited by 3 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the realm of wetland remote sensing image segmentation, this study introduces the application of the ConvNeXt model. Recognized for its expertise in processing highresolution imagery and conducting multi-scale feature extraction, ConvNeXt proves particularly effective for the analysis of the intricate spectral-spatial characteristics inherent to wetland landscapes [36]. The advanced interpretative abilities of this model not only propose an innovative methodology for wetland segmentation but also establish a pioneering standard for subsequent studies utilizing deep learning within complex ecosystems.…”

Section: Convnext Modelmentioning

confidence: 99%

A Novel CA-RegNet Model for Macau Wetlands Auto Segmentation Based on GF-2 Remote Sensing Images

Li,

Cui,

Tian

2023

Applied Sciences

View full text Add to dashboard Cite

Wetlands, situated at the vital intersection of terrestrial and aquatic ecosystems, are pivotal in preserving global biodiversity and maintaining environmental equilibrium. The escalating trend of global urbanization necessitates the utilization of high-resolution satellite imagery for accurate wetland delineation, which is essential for establishing efficacious conservation strategies. This study focuses on the wetlands of Macau, characterized by distinctive coastal and urban features. A noteworthy enhancement in this study is the integration of the Coordinate Attention mechanism with the RegNet model, forming the CA-RegNet. This combined model demonstrates superior performance, outdoing previous Macau wetlands segmentation studies that used ResNet, evidenced by an approximate rise of 2.7% in overall accuracy (OA), 4.0% in the Kappa coefficient, 1.9% in the mAcc, and 0.5% in the mIoU. Visual evaluations of the segmentation results reinforce the competence of the CA-RegNet model in precisely demarcating coastal wetlands and Saiwan Lake, thereby overcoming the former constraints of ResNet and underscoring the robustness and innovation of this study.

show abstract

Section: Convnext Modelmentioning

confidence: 99%

A Novel CA-RegNet Model for Macau Wetlands Auto Segmentation Based on GF-2 Remote Sensing Images

Li,

Cui,

Tian

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

Real-Time Corn Variety Recognition Using an Efficient DenXt Architecture with Lightweight Optimizations

Zhao,

Liu,

Han

et al. 2025

Agriculture

View full text Add to dashboard Cite

As a pillar grain crop in China’s agriculture, the yield and quality of corn are directly related to food security and the stable development of the agricultural economy. Corn varieties from different regions have significant differences inblade, staminate and root cap characteristics, and these differences provide a basis for variety classification. However, variety characteristics may be mixed in actual cultivation, which increases the difficulty of identification. Deep learning classification research based on corn nodulation features can help improve classification accuracy, optimize planting management, enhance production efficiency, and promote the development of breeding and production technologies. In this study, we established a dataset of maize plants at the elongation stage containing 31,000 images of 40 different types, including corn leaves, staminates, and root caps, and proposed a DenXt framework model. Representative Batch Normalization (RBN) is introduced into the DenseNet-121 model to improve the generalization ability of the model, and the SE module and deep separable convolution are integrated to enhance the feature representation and reduce the computational complexity, and the Dropout regularization is introduced to further improve the generalization ability of the model and reduce the overfitting. The proposed network model achieves a classification accuracy of 97.79%, which outperforms VGG16, Mobilenet V3, ResNet50 and ConvNeXt image classification models in terms of performance. Compared with the original DenseNet 121 network model, the DenXt model improved the classification accuracy by 3.23% and reduced the parameter count by 32.65%. In summary, the new approach addresses the challenges of convolutional neural networks and provides easy-to-deploy lightweight networks to support corn variety recognition applications.

show abstract

A Mixture Model for Fruit Ripeness Identification in Deep Learning

Xiao,

Nguyen,

Yan

2023

Handbook of Research on AI and ML for Intelligent Machines and Systems

View full text Add to dashboard Cite

Visual object detection is a foundation in the field of computer vision. Since the size of visual objects in an images is various, the speed and accuracy of object detection are the focus of current research projects in computer vision. In this book chapter, the datasets consist of fruit images with various maturity. Different types of fruit are divided into the classes “ripe” and “overripe” according to the degree of skin folds. Then the object detection model is employed to automatically classify different ripeness of fruits. A family of YOLO models are representative algorithms for visual object detection. The authors make use of ConvNeXt and YOLOv7, which belong to the CNN network, to locate and detect fruits, respectively. YOLOv7 employs the bag-of-freebies training method to achieve its objectives, which reduces training costs and enhances detection accuracy. An extended E-ELAN module, based on the original ELAN, is proposed within YOLOv7 to increase group convolution and improve visual feature extraction. In contrast, ConvNeXt makes use of a standard neural network architecture, with ResNet-50 serving as the baseline. The authors compare the proposed models, which result in an optimal classification model with best precision of 98.9%.

show abstract

Conv2NeXt: Reconsidering Conv NeXt Network Design for Image Recognition

Cited by 3 publications

References 36 publications

A Novel CA-RegNet Model for Macau Wetlands Auto Segmentation Based on GF-2 Remote Sensing Images

A Novel CA-RegNet Model for Macau Wetlands Auto Segmentation Based on GF-2 Remote Sensing Images

Real-Time Corn Variety Recognition Using an Efficient DenXt Architecture with Lightweight Optimizations

A Mixture Model for Fruit Ripeness Identification in Deep Learning

Contact Info

Product

Resources

About