vit：An Image is Worth 16x16 Words：Transformers for Image Recognition at Scale

太棒了! 目前共计 241 篇日志。 继续努力。

2022

06-23

vit：An Image is Worth 16x16 Words：Transformers for Image Recognition at Scale

06-20

SETR：Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

06-19

BiSeNetv3：Rethinking BiSeNet For Real-time Semantic Segmentation

06-17

BiSeNet V2：Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

06-15

CFPNet：Channel-wise Feature Pyramid for Real-Time Semantic Segmentation

04-26

YOLACT++：Better Real-time Instance Segmentation

04-21

FCOS：Fully Convolutional One-Stage Object Detection

04-05

SOLOv2：Dynamic and Fast Instance Segmentation