Transformer
文章平均质量分 88
CV小白升级中
CV算法从业者共勉
展开
-
Transformer系列:Pyramid Vision Transformer(PVT) v2 (CVMJ 2022)
PVTv2 reduces the computational complexity of PVTv1 to linear and achieves significant improvements on fundamental vision tasks原创 2022-06-23 15:54:04 · 1013 阅读 · 1 评论 -
Transformer系列:Pyramid Vision Transformer (ICCV2021)
PVT overcomes the difficulties of porting Transformer to various dense prediction tasks.原创 2022-06-23 11:29:52 · 1949 阅读 · 0 评论 -
Transformer系列:Shunted self-attention (CVPR2022 oral)
The key idea of SSA is to inject heterogeneous receptive field sizes into tokens: before computing the self-attention matrix, it selectively merges tokens to represent larger object features while keeping certain tokens to preserve fine-grained features.原创 2022-06-22 11:53:41 · 262 阅读 · 0 评论 -
Transformer系列:Classification --> ViT (ICLR2021)
1. Motivation2. Method3.Experiment原创 2021-06-10 20:55:55 · 857 阅读 · 2 评论 -
Transformer系列:Detection--> Deformable DETR (ICLR2021)
文章地址:https://arxiv.org/pdf/2010.04159.pdf原创 2021-06-10 19:34:16 · 1359 阅读 · 4 评论