List your company
ResearchFormerly WizWand

Image Classification on Oxford Flowers (Top-1/Top-5 Accuracy)

74.03Top-1 AccuracySimple Averaging w/ E-PMQ
15.665230.817645.9761.1224Mar 27, 2026Apr 4, 2026Apr 12, 2026Apr 21, 2026Apr 29, 2026May 7, 2026May 16, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Simple Averaging w/ E-PMQMerging Strategy=Simple Averaging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0574.03—
TIES-Merging w/ E-PMQMerging Strategy=TIES-Merging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0572.37—
WUDI-Merging w/ E-PMQMerging Strategy=WUDI-Merging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0570.37—
Task Arithmetic w/ E-PMQMerging Strategy=Task Arithmetic, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0569.69—
Simple AveragingMerging Strategy=Simple Averaging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.0567.4—
Simple Averaging w/ GPTQMerging Strategy=Simple Averaging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0564.35—
WUDI-MergingMerging Strategy=WUDI-Merging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.0563.8—
WUDI-Merging w/ GPTQMerging Strategy=WUDI-Merging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0561.26—
Simple Averaging w/ RTNMerging Strategy=Simple Averaging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0560.56—
Simple Averaging w/ AWQMerging Strategy=Simple Averaging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0559.88—
TIES-MergingMerging Strategy=TIES-Merging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.0558.2—
WUDI-Merging w/ AWQMerging Strategy=WUDI-Merging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0555.68—
TIES-Merging w/ GPTQMerging Strategy=TIES-Merging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0555.6—
WUDI-Merging w/ RTNMerging Strategy=WUDI-Merging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0554.92—
TIES-Merging w/ RTNMerging Strategy=TIES-Merging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0550.54—
TIES-Merging w/ AWQMerging Strategy=TIES-Merging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0550.2—
Task ArithmeticMerging Strategy=Task Arithmetic, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.0538.6—
Task Arithmetic w/ GPTQMerging Strategy=Task Arithmetic, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0535.92—
Task Arithmetic w/ AWQMerging Strategy=Task Arithmetic, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0534.62—
Task Arithmetic w/ RTNMerging Strategy=Task Arithmetic, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0532.38—
CE+SIL+SupCon2Loss function=Cross-Entropy + Silhouette + SupCon22026.0327.456.11
CE+SILLoss function=Cross-Entropy + Silhouette2026.0326.5654.56
ProxyNCALoss function=Proxy Neighborhood Component Analysis2026.0322.1—
SupCon2Loss function=Supervised Contrastive (two-view)2026.0321.0650.25
CenterLoss function=Center Loss2026.0320.1847.89
CELoss function=Cross-Entropy2026.0319.647.21
SupConLoss function=Supervised Contrastive2026.0317.9146.54