Channel grouping vision transformer for lightweight fruit and vegetable recognition

Open Webpage

Chengxu Liu, Weiqing Min, Jingru Song, Yancun Yang, Guorui Sheng, Tao Yao, Lili Wang, Shuqiang Jiang

Published: 2025, Last Modified: 16 Jan 2026Expert Syst. Appl. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We adopt a Channel Grouping Vision Transformer (CGViT) for lightweight fruit and vegetable recognition.•We benchmark various lightweight deep learning networks on these four fruit datasets.•Evaluations on four fruit and vegetable datasets demonstrate that our approach achieves state-of-the-art performance while consuming fewer resources.