Lightweight image super-resolution network using involution

Jiu, Liang; Xue, Jiangbo; Zhang, Yu; Hu, Yanda

doi:10.1007/s00138-022-01307-9

Cited by 4 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And contrast learning to achieve efficient SISR, which effectively reduced the computational cost and achieves high performance. Liang et al (2022) proposed two building blocks based on involution, which were lighter and more efficient than the traditional convolution-based modules, to achieve a lightweight image super-resolution network.…”

Section: Involution Operatormentioning

confidence: 99%

A Hybrid Text Recognition Approach based on Involution Operators and Graph Convolution Neural Networks

Tong

Dong

et al. 2023

Preprint

View full text Add to dashboard Cite

Scene text recognition as a subsequent task of text detection is to convert the detected text regions into computer readable and editable characters, words or text lines. To improve the recognition of long text, a text recognition method based on the involution operator and graph convolutional network (GCN) is proposed. The method builds a new feature sequence extraction network based on the involution operator, which can extract text features within a larger sense field and generate feature sequences. Furthermore, the addition of gate recurrent unit (GRU) and GCN can help the model to remember useful text features while forgetting useless visual information, and enhance the contextual semantic information of feature sequences from multiple perspectives. Comparative experiments on ICDAR (International Conference on Document Analysis and Recognition) 2013, ICDAR 2015 and SVT (Street View Text) datasets show that the method can effectively recognize multi-scale ambiguous and adherent text. The F-score reaches 94.2%, 89.7%, and 93.8% without lexicon supervision, respectively.

show abstract

Section: Involution Operatormentioning

confidence: 99%