Vision Transformer with Spatial 2D Multi-Channel Tokens
Electronics · 23.06.2026 · 15 (13) · 2752
DOI: 10.3390/electronics15132752 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 23.06.2026. Verfasst von Sirui Zheng und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Vision Transformer (ViT) has been widely adopted in the computer vision community. However, the standard ViT often contains many parameters, usually performs poorly when trained from scratch on medium-scale datasets, and does not explicitly preserve the local spatial and channel-wise structures within each token. This work proposes a novel model called the Token-Shared Convolutional Projection Vision Transformer (TSCP-ViT). The core idea of TSCP-ViT is to integrate convolutional layers into the multi-head attention mechanism and to apply the same convolutional operation independently to each token, where each token exhibits spatial 2D multi-channel characteristics. In addition, this work introduces a Transformer decoder immediately after each Transformer encoder, enabling the classification tokens to aggregate information from all tokens and be updated using statistical information. Moreover, a trainable Non-Reversing Gate GELU (NRG-GELU) activation is also proposed. Comparative experiments on CIFAR-100, Food-101, and ImageNet100 show that, under comparable parameter counts and without pretraining or knowledge distillation, TSCP-ViT substantially surpasses ViT, outperforms CvT, outperforms ResNet on Food-101, and approaches ResNet on CIFAR-100 and ImageNet100, although with considerably higher FLOPs.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zheng, S., Li, Y., Zhang, Z., & Zhao, D. (2026). Vision Transformer with Spatial 2D Multi-Channel Tokens. Electronics, 15(13), 2752. https://doi.org/10.3390/electronics15132752
Vancouver
Zheng S, Li Y, Zhang Z, Zhao D. Vision Transformer with Spatial 2D Multi-Channel Tokens. Electronics. 2026;15(13):2752. doi:10.3390/electronics15132752
BibTeX
@article{Zheng2026,
author = {Zheng, Sirui and Li, Yu and Zhang, Zhongxiang and Zhao, Dequn},
title = {Vision Transformer with Spatial 2D Multi-Channel Tokens},
journal = {Electronics},
year = {2026},
volume = {15},
number = {13},
pages = {2752},
doi = {10.3390/electronics15132752}
}
EUVIMED