Crowd Counting On Trancos

MAE

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	MAE	Paper Title	Repository
CSRNet	3.56	CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
S-DCNet	2.92	From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer	-
ADCrowdNet	2.44	ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding
M-SFANet+M-SegNet	2.22	Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting

0 of 4 row(s) selected.