List your company
ResearchFormerly WizWand

Image Classification on ImageNet 1k (Top-1 Acc., Retention)

85.51Top-1 AccuracyConvNeXt-B
14.051632.603351.15569.7067Jul 17, 2025
Updated 7mo ago

Evaluation results

MethodLinks
ConvNeXt-BModel=ConvNeXt-B, Method (Full vs VBP)=Full, MACs (G)=15.38, Parameters (M)=88.592025.0785.51—
ConvNeXt-SModel=ConvNeXt-S, Method (Full vs VBP)=Full, MACs (G)=8.71, Parameters (M)=50.222025.0784.57—
VBPModel=ConvNeXt-B, Method (Full vs VBP)=VBP, MACs (G)=8.91 (-42.1%), Parameters (M)=41.32 (-53.4%), Pruning Rate=50%, Evaluation Condition=VBP (Final)2025.0783.497.6
ConvNeXt-TModel=ConvNeXt-T, Method (Full vs VBP)=Full, MACs (G)=4.47, Parameters (M)=28.592025.0782.9—
VBPModel=ConvNeXt-S, Method (Full vs VBP)=VBP, MACs (G)=5.11 (-41.3%), Parameters (M)=23.50 (-53.2%), Pruning Rate=50%, Evaluation Condition=VBP (Final)2025.0782.8297.9
VBPModel=ConvNeXt-T, Method (Full vs VBP)=VBP, MACs (G)=2.96 (-33.8%), Parameters (M)=12.61 (-55.9%), Pruning Rate=50%, Evaluation Condition=VBP (Final)2025.0781.398.1
VBPModel=ConvNeXt-B, Method (Full vs VBP)=VBP, MACs (G)=8.91 (-42.1%), Parameters (M)=41.32 (-53.4%), Pruning Rate=50%, Evaluation Condition=Retention (Pre-finetuning)2025.0757.166.8
VBPModel=ConvNeXt-S, Method (Full vs VBP)=VBP, MACs (G)=5.11 (-41.3%), Parameters (M)=23.50 (-53.2%), Pruning Rate=50%, Evaluation Condition=Retention (Pre-finetuning)2025.0730.9236.6
VBPModel=ConvNeXt-T, Method (Full vs VBP)=VBP, MACs (G)=2.96 (-33.8%), Parameters (M)=12.61 (-55.9%), Pruning Rate=50%, Evaluation Condition=Retention (Pre-finetuning)2025.0716.820.3