Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:convolutional_neural_network
|
| gptkbp:application |
image classification
object detection semantic segmentation |
| gptkbp:arXivID |
2111.11418
|
| gptkbp:author |
Jiehao Wang
Han Hu Qiwen Liu Xiaohan Wang Yunhao Wang |
| gptkbp:bench |
gptkb:COCO
gptkb:ImageNet gptkb:ADE20K |
| gptkbp:component |
pooling layer
|
| gptkbp:designedFor |
computer vision
|
| gptkbp:developedBy |
gptkb:Meta_AI
|
| gptkbp:introducedIn |
2022
|
| gptkbp:notableFeature |
parameter efficiency
competitive accuracy simple architecture |
| gptkbp:notablePublication |
MetaFormer is Actually What You Need for Vision
|
| gptkbp:openSource |
yes
|
| gptkbp:relatedTo |
MetaFormer
|
| gptkbp:replacedBy |
self-attention
|
| gptkbp:repository |
https://github.com/sail-sg/poolformer
|
| gptkbp:bfsParent |
gptkb:Hugging_Face_models
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
PoolFormer
|