Hybrid ResNet based on joint basic and attention modules for long-tailed classification

Zhao, Wei; Su, Yuling; Hu, Minjie; Zhao, Hong

doi:10.1016/j.ijar.2022.08.007

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By virtue of this architectural innovation, VGG has not only expanded the network's capacity to extract intricate features but has also elevated its overall classification accuracy. In a similar vein, ResNet (Zhao et al, 2022) and DenseNet (Albahli et al, 2021) have introduced groundbreaking concepts in neural network design. ResNet exploits residual connectivity, allowing the network to perform tens of thousands of iterations without succumbing to vanishing gradient problems.…”

Section: Introductionmentioning

confidence: 99%

Design of a MobilNetV2-Based Retrieval System for Traditional Cultural Artworks

Cao,

Cao

2023

International Journal of Gaming and Computer-Mediated Simulations

View full text Add to dashboard Cite

Aiming at the problem that it is difficult for art teachers to take into account each student in the art appreciation education in colleges and universities, this paper proposes a retrieval system for traditional cultural works of art. Dense connections are used to replace residual connections between bottlenecks in MobileNetV2 network and gradient transmission in the network. The dilution factor is used to control the size of the network to solve the problem of the rapid increase in the number of network channels. In addition, the non-local attention mechanism is effectively combined with the improved MobileNetV2 network structure, which effectively improves the classification accuracy of the network. Compared with VGG16, ResNet18, and ResNet34, the classification accuracy is increased by 21.3%, 9.2%, and 3%, respectively. The method in this paper has achieved good results in the classification of art works. According to the images of art works to be appreciated, it helps students understand the relevant cultural knowledge independently and reduce the burden of teachers.

show abstract

Section: Introductionmentioning

confidence: 99%

Design of a MobilNetV2-Based Retrieval System for Traditional Cultural Artworks

Cao,

Cao

2023

International Journal of Gaming and Computer-Mediated Simulations

View full text Add to dashboard Cite

show abstract

(Retracted) Design of street art image retrieval system based on virtual simulation technology for the public health environment

Li¹,

Hua²

2023

J. Electron. Imag.

View full text Add to dashboard Cite

The Editor-in-Chief and the publisher have retracted this article, which was submitted as part of a guest-edited special section. An investigation uncovered evidence of systematic manipulation of the publication process, including compromised peer review. The Editor and publisher no longer have confidence in the results and conclusions of the article.ZL and JH either did not respond directly or could not be reached.

show abstract

Hybrid ResNet based on joint basic and attention modules for long-tailed classification

Cited by 2 publications

References 34 publications

Design of a MobilNetV2-Based Retrieval System for Traditional Cultural Artworks

Design of a MobilNetV2-Based Retrieval System for Traditional Cultural Artworks

(Retracted) Design of street art image retrieval system based on virtual simulation technology for the public health environment

Contact Info

Product

Resources

About