83 citations · 95 across the 4 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
EDIT: Enhancing Vision Transformers by Mitigating Attention Sink through an Encoder-Decoder Architecture
Wenfeng Feng, Hongxiang Wang, Jianlong Wang +5
In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. A…
cs.CV2019★ 3 cited
ResNetX: a more disordered and deeper network architecture
Wenfeng Feng, Xin Zhang, Guangpeng Zhao
Designing efficient network structures has always been the core content of neural network research. ResNet and its variants have proved to be efficient in architecture. However, ho…