List your company
ResearchFormerly WizWand

Image Classification on GTSRB (Top-1 Accuracy)

98.9Top-1 AccuracyFine-tuned (STL)
7.931.52555.1578.775Mar 3, 2026Mar 15, 2026Mar 27, 2026Apr 9, 2026Apr 21, 2026May 3, 2026May 16, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Fine-tuned (STL)Backbone=CLIP-ViT-B/32, Bit-width=Full-precision, Training=Single-task learning2026.0598.9
WUDI-MergingMerging Method=WUDI-Merging, Quantization Method=None, Bit-width=Full-precision, Model Backbone=CLIP-ViT-L/142026.0598
WUDI-MergingBackbone=CLIP-ViT-B/32, Merging Strategy=WUDI-Merging, Bit-width=Full-precision2026.0594.9
WUDI-MergingMerging Strategy=WUDI-Merging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.0591.5
WUDI-Merging w/ E-PMQMerging Method=WUDI-Merging, Quantization Method=E-PMQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0588.9
WUDI-Merging w/ GPTQMerging Method=WUDI-Merging, Quantization Method=GPTQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0588.4
WUDI-Merging w/ RTNMerging Method=WUDI-Merging, Quantization Method=RTN, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0588.2
TIES-MergingMerging Method=TIES-Merging, Quantization Method=None, Bit-width=Full-precision, Model Backbone=CLIP-ViT-L/142026.0585.2
WUDI-Merging w/ AWQMerging Method=WUDI-Merging, Quantization Method=AWQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0584.3
Task ArithmeticMerging Method=Task Arithmetic, Quantization Method=None, Bit-width=Full-precision, Model Backbone=CLIP-ViT-L/142026.0583.5
WUDI-MergingMerging Strategy=WUDI-Merging, Quantization Method=Full-precision, Bit-width=Full, Backbone=CLIP-ViT-B/322026.0582.9
WUDI-Merging w/ GPTQBackbone=CLIP-ViT-B/32, Merging Strategy=WUDI-Merging, Quantization Algorithm=GPTQ, Bit-width=4-bit2026.0581.3
WUDI-Merging w/ E-PMQBackbone=CLIP-ViT-B/32, Merging Strategy=WUDI-Merging, Quantization Algorithm=E-PMQ, Bit-width=4-bit2026.0580.6
WUDI-Merging w/ AWQBackbone=CLIP-ViT-B/32, Merging Strategy=WUDI-Merging, Quantization Algorithm=AWQ, Bit-width=4-bit2026.0580.2
WUDI-Merging w/ RTNBackbone=CLIP-ViT-B/32, Merging Strategy=WUDI-Merging, Quantization Algorithm=RTN, Bit-width=4-bit2026.0580
WUDI-Merging w/ GPTQMerging Strategy=WUDI-Merging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0577.57
WUDI-Merging w/ AWQMerging Strategy=WUDI-Merging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0577.09
Simple Averaging w/ E-PMQMerging Method=Simple Averaging, Quantization Method=E-PMQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0576.8
Task Arithmetic w/ E-PMQMerging Method=Task Arithmetic, Quantization Method=E-PMQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0576.5
TIES-Merging w/ E-PMQMerging Method=TIES-Merging, Quantization Method=E-PMQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0576.4
TIES-Merging w/ RTNMerging Method=TIES-Merging, Quantization Method=RTN, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0576.3
WUDI-Merging w/ E-PMQMerging Strategy=WUDI-Merging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0576.18
WUDI-Merging w/ RTNMerging Strategy=WUDI-Merging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0576.03
TIES-Merging w/ GPTQMerging Method=TIES-Merging, Quantization Method=GPTQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0575.9
Simple AveragingMerging Method=Simple Averaging, Quantization Method=None, Bit-width=Full-precision, Model Backbone=CLIP-ViT-L/142026.0574
WUDI-Merging + E-PMQMerging Strategy=WUDI-Merging, Quantization Method=E-PMQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0573.9
Task Arithmetic w/ GPTQMerging Method=Task Arithmetic, Quantization Method=GPTQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0573.2
Task Arithmetic w/ RTNMerging Method=Task Arithmetic, Quantization Method=RTN, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0572.7
WUDI-Merging + GPTQMerging Strategy=WUDI-Merging, Quantization Method=GPTQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0571.84
WUDI-Merging + AWQMerging Strategy=WUDI-Merging, Quantization Method=AWQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0569.96
WUDI-Merging + RTNMerging Strategy=WUDI-Merging, Quantization Method=RTN, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0569.52
TIES-MergingBackbone=CLIP-ViT-B/32, Merging Strategy=TIES-Merging, Bit-width=Full-precision, Lambda=0.32026.0569.4
Simple Averaging w/ GPTQMerging Method=Simple Averaging, Quantization Method=GPTQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0569
Simple Averaging w/ RTNMerging Method=Simple Averaging, Quantization Method=RTN, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0568.8
Task ArithmeticBackbone=CLIP-ViT-B/32, Merging Strategy=Task Arithmetic, Bit-width=Full-precision, Lambda=0.32026.0568.5
TIES-MergingMerging Strategy=TIES-Merging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.0563.9
TIES-Merging w/ AWQMerging Method=TIES-Merging, Quantization Method=AWQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0563.5
TIES-Merging w/ GPTQBackbone=CLIP-ViT-B/32, Merging Strategy=TIES-Merging, Quantization Algorithm=GPTQ, Bit-width=4-bit, Lambda=0.32026.0562.9
DINORANKCLIPProtocol=Linear probing2026.0562.1
RANKCLIPProtocol=Linear probing2026.0560.6
CLIPProtocol=Linear probing2026.0560
TIES-Merging w/ RTNBackbone=CLIP-ViT-B/32, Merging Strategy=TIES-Merging, Quantization Algorithm=RTN, Bit-width=4-bit, Lambda=0.32026.0559.8
Simple Averaging w/ E-PMQBackbone=CLIP-ViT-B/32, Merging Strategy=Simple Averaging, Quantization Algorithm=E-PMQ, Bit-width=4-bit2026.0559.5
TIES-Merging w/ AWQBackbone=CLIP-ViT-B/32, Merging Strategy=TIES-Merging, Quantization Algorithm=AWQ, Bit-width=4-bit, Lambda=0.32026.0559.3
TIES-Merging w/ E-PMQBackbone=CLIP-ViT-B/32, Merging Strategy=TIES-Merging, Quantization Algorithm=E-PMQ, Bit-width=4-bit, Lambda=0.32026.0559.2
Task Arithmetic w/ AWQMerging Method=Task Arithmetic, Quantization Method=AWQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0558.8
CyCLIPProtocol=Linear probing2026.0558.6
TIES-Merging w/ GPTQMerging Strategy=TIES-Merging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0557.85
TIES-MergingMerging Strategy=TIES-Merging, Quantization Method=Full-precision, Bit-width=Full, Backbone=CLIP-ViT-B/322026.0557.7
TIES-Merging w/ RTNMerging Strategy=TIES-Merging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0557.24
Task Arithmetic w/ GPTQBackbone=CLIP-ViT-B/32, Merging Strategy=Task Arithmetic, Quantization Algorithm=GPTQ, Bit-width=4-bit, Lambda=0.32026.0557
Task Arithmetic w/ E-PMQBackbone=CLIP-ViT-B/32, Merging Strategy=Task Arithmetic, Quantization Algorithm=E-PMQ, Bit-width=4-bit, Lambda=0.32026.0557
TIES-Merging w/ AWQMerging Strategy=TIES-Merging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0556.48
Task Arithmetic w/ AWQBackbone=CLIP-ViT-B/32, Merging Strategy=Task Arithmetic, Quantization Algorithm=AWQ, Bit-width=4-bit, Lambda=0.32026.0555.6
ITOPre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.0355.5
Simple AveragingBackbone=CLIP-ViT-B/32, Merging Strategy=Simple Averaging, Bit-width=Full-precision2026.0554.9
Task Arithmetic w/ RTNBackbone=CLIP-ViT-B/32, Merging Strategy=Task Arithmetic, Quantization Algorithm=RTN, Bit-width=4-bit, Lambda=0.32026.0554.6
Simple Averaging w/ E-PMQMerging Strategy=Simple Averaging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0554.32
CLIPPre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.0354.1
Simple Averaging + E-PMQMerging Strategy=Simple Averaging, Quantization Method=E-PMQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0553.44
TIES-Merging w/ E-PMQMerging Strategy=TIES-Merging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0553.36
Simple Averaging w/ AWQMerging Method=Simple Averaging, Quantization Method=AWQ, Bit-width=4-bit, Model Backbone=CLIP-ViT-L/142026.0552.3
CLIPBackbone=ViT-L/16, Pre-training Dataset=DataComp-1B, Training Epochs=1, Evaluation Protocol=Zero-shot2026.0352.1
ALIPProtocol=Linear probing2026.0551.5
Task Arithmetic w/ E-PMQMerging Strategy=Task Arithmetic, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0551.5
TIES-Merging + E-PMQMerging Strategy=TIES-Merging, Quantization Method=E-PMQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0551.37
TIES-Merging + GPTQMerging Strategy=TIES-Merging, Quantization Method=GPTQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0550.53
TIES-Merging + AWQMerging Strategy=TIES-Merging, Quantization Method=AWQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0549.74
Simple Averaging w/ AWQBackbone=CLIP-ViT-B/32, Merging Strategy=Simple Averaging, Quantization Algorithm=AWQ, Bit-width=4-bit2026.0549.6
Simple Averaging w/ GPTQBackbone=CLIP-ViT-B/32, Merging Strategy=Simple Averaging, Quantization Algorithm=GPTQ, Bit-width=4-bit2026.0549.1
ITOBackbone=ViT-L/16, Pre-training Dataset=DataComp-1B, Training Epochs=1, Evaluation Protocol=Zero-shot2026.0349
Task ArithmeticMerging Strategy=Task Arithmetic, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.0548.4
TIES-Merging + RTNMerging Strategy=TIES-Merging, Quantization Method=RTN, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0547.81
Simple Averaging w/ RTNBackbone=CLIP-ViT-B/32, Merging Strategy=Simple Averaging, Quantization Algorithm=RTN, Bit-width=4-bit2026.0547.7
ITO sub2Backbone=ViT-L/16, Pre-training Dataset=DataComp-1B, Training Epochs=1, Evaluation Protocol=Zero-shot2026.0347.3
Task Arithmetic + E-PMQMerging Strategy=Task Arithmetic, Quantization Method=E-PMQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0546.66
ITO sub2Pre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.0345.9
Simple AveragingMerging Strategy=Simple Averaging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.0545.6
Task Arithmetic w/ GPTQMerging Strategy=Task Arithmetic, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0544.19
Simple Averaging w/ GPTQMerging Strategy=Simple Averaging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0544.17
Simple Averaging w/ AWQMerging Strategy=Simple Averaging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0543.95
Simple AveragingMerging Strategy=Simple Averaging, Quantization Method=Full-precision, Bit-width=Full, Backbone=CLIP-ViT-B/322026.0543.1
Simple Averaging + GPTQMerging Strategy=Simple Averaging, Quantization Method=GPTQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0542.76
Simple Averaging w/ RTNMerging Strategy=Simple Averaging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0542.64
Simple Averaging + AWQMerging Strategy=Simple Averaging, Quantization Method=AWQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0542.42
Task Arithmetic w/ RTNMerging Strategy=Task Arithmetic, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0541.37
Task Arithmetic w/ AWQMerging Strategy=Task Arithmetic, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.0540.91
ITOZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.0340.7
Simple Averaging + RTNMerging Strategy=Simple Averaging, Quantization Method=RTN, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0540.59
CLIPZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.0338.2
SLIPZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.0335.5
Pre-trainedBackbone=CLIP-ViT-B/32, Bit-width=Full-precision2026.0532.5
Task ArithmeticMerging Strategy=Task Arithmetic, Quantization Method=Full-precision, Bit-width=Full, Backbone=CLIP-ViT-B/322026.0529.8
Task Arithmetic + AWQMerging Strategy=Task Arithmetic, Quantization Method=AWQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0527.58
Task Arithmetic + RTNMerging Strategy=Task Arithmetic, Quantization Method=RTN, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0527.51
Task Arithmetic + GPTQMerging Strategy=Task Arithmetic, Quantization Method=GPTQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.0527.19
ITO sub2Pre-training Dataset=CC12M, Backbone=ViT-B/16, Epochs=30, Evaluation protocol=Zero-shot2026.0313.1
CLIPPre-training Dataset=CC12M, Backbone=ViT-B/16, Epochs=30, Evaluation protocol=Zero-shot2026.0312.9
ITO sub2Backbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.0311.9
FLAIRBackbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.0311.4