Image Models

MetaFormer

Introduced by Yu et al. in MetaFormer Is Actually What You Need for Vision

MetaFormer is a general architecture abstracted from Transformers by not specifying the token mixer.

Source: MetaFormer Is Actually What You Need for Vision

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Classification 8 16.67%
Semantic Segmentation 8 16.67%
Object Detection 6 12.50%
Image Segmentation 3 6.25%
Medical Image Segmentation 3 6.25%
Specificity 2 4.17%
Decoder 2 4.17%
Autonomous Driving 1 2.08%
Object 1 2.08%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories