List your company
ResearchFormerly WizWand

GPU Memory Usage on AutoPET-II for Medical Image Segmentation

488Peak GPU Memory Usage (Training)Slim UNETR
-181.124,335.448,85213,368.56Sep 26, 2025
Updated 4mo ago

Evaluation results

MethodLinks
Slim UNETRType=CNN-Transformer, Batch size=22025.09488106
VeloxSegType=CNN-Transformer, Batch size=22025.09842152
U-KANType=CNN-KAN, Batch size=22025.092,138558
SegFormer-3DType=CNN-Transformer, Batch size=22025.092,272426
H-DenseFormerType=CNN-Transformer, Batch size=22025.093,1721,256
UNETR++Type=CNN-Transformer, Batch size=22025.093,392940
VNetType=CNN, Batch size=22025.093,8201,762
UNETRType=CNN-Transformer, Batch size=22025.094,1141,788
NestedFormerType=CNN-Transformer, Batch size=22025.094,4281,658
U-RWKVType=CNN-RWKV, Batch size=22025.094,582900
UNetType=CNN, Batch size=22025.095,0542,268
HCMA-UNetType=CNN-Mamba, Batch size=22025.097,7301,480
A2FSegType=CNN, Batch size=22025.097,7482,004
SuperLightNetType=CNN-Transformer, Batch size=22025.097,8122,510
Swin UNETRType=CNN-Transformer, Batch size=22025.0911,1642,616
VSmTransType=CNN-Transformer, Batch size=22025.0913,8561,956
MedNeXtType=CNN, Batch size=22025.0917,2163,678