most citedM2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition

4 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions

1 paper

cs.CV2023★ 4 cited

M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition

Jiyong Moon, Junseok Lee, Yunju Lee +1

Recently, vision Transformers (ViTs) have been actively applied to fine-grained visual recognition (FGVR). ViT can effectively model the interdependencies between patch-divided obj…