List your company
ResearchFormerly WizWand

Image Classification on FER 2013

0.998Top-1 AccCLIP
0.177440.390470.60350.81653Aug 4, 2022Mar 22, 2023Nov 7, 2023Jun 24, 2024Feb 9, 2025Sep 27, 2025May 16, 2026
Updated 5mo ago

Evaluation results

MethodLinks
CLIPPre-training Data=WIT-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.070.998——
CLIP+Pre-training Data=WIT-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.070.998——
MLCDPre-training Data=LAION-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.070.993——
OpenCLIPPre-training Data=LAION-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.070.992——
UNICOMPre-training Data=LAION-400M, Backbone=ViT-L/14, Evaluation Protocol=Linear Probe2024.070.985——
X-FM_baseLinear evaluation=true, Model size=Base, Patch size=16*16, Resolution=224*2242023.010.726——
CLIPLinear evaluation=true, Model size=Base, Patch size=16*16, Resolution=224*2242023.010.695——
DaVinciLinear evaluation=true, Model size=Base, Patch size=16*16, Resolution=224*2242023.010.684——
WUDI-MergingMerging Strategy=WUDI-Merging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.050.642——
RN50 BaselineIR=16, Backbone=ResNet-502026.010.63——
FLAVALinear evaluation=true, Model size=Base, Patch size=16*16, Resolution=224*2242023.010.611——
OpenCLIP-G/14Zero-shot=true2024.020.596——
LoRA+Parameter Count=0.67M2025.120.5951——
AdaLoRAParameter Count=0.67M2025.120.5932——
EVA-CLIP-18BZero-shot=true2024.020.593——
DoRAParameter Count=0.77M2025.120.591——
EVA-02-CLIP-E/14+Zero-shot=true2024.020.59——
VeRAParameter Count=0.10M2025.120.5881——
Partial-AdaLoRAParameter Count=0.21M2025.120.5877——
Partial-LoRAParameter Count=0.21M2025.120.5861——
SmartCLIPBackbone=ViT-L/14, Zero-shot=true2025.070.586——
xCLIPLinear probing=true, Backbone=ViT-B/16, Pre-train=IT35M2022.100.585——
WUDI-MergingMerging Strategy=WUDI-Merging, Quantization Method=Full-precision, Bit-width=Full, Backbone=CLIP-ViT-B/322026.050.585——
LoRAParameter Count=0.67M2025.120.5796——
LongCLIPBackbone=ViT-L/14, Zero-shot=true2025.070.578——
CLIPmode=zero-shot2022.080.577——
CLIPLinear probing=true, Backbone=ViT-B/16, Pre-train=IT35M2022.100.565——
InternVL-CZero-shot=true2024.020.562——
DFN5B-CLIP-H/14+Zero-shot=true2024.020.561——
EVA-CLIP-8BZero-shot=true2024.020.561——
EVA-01-CLIP-g/14+Zero-shot=true2024.020.56——
TIES-MergingMerging Strategy=TIES-Merging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.050.549——
nCLIPLinear probing=true, Backbone=ViT-B/16, Pre-train=IT35M2022.100.547——
DFN5B-CLIP-H/14Zero-shot=true2024.020.547——
LOUPEmode=zero-shot2022.080.533——
EVA-01-CLIP-g/14Zero-shot=true2024.020.522——
Simple AveragingMerging Strategy=Simple Averaging, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.050.516——
Simple AveragingMerging Strategy=Simple Averaging, Quantization Method=Full-precision, Bit-width=Full, Backbone=CLIP-ViT-B/322026.050.502——
CLIPBackbone=ViT-L/14, Zero-shot=true2025.070.49——
TIES-MergingMerging Strategy=TIES-Merging, Quantization Method=Full-precision, Bit-width=Full, Backbone=CLIP-ViT-B/322026.050.473——
Noun SubmanifoldBackbone=CLIP ViT-L-14, zero-shot=true2023.050.464——
Task ArithmeticMerging Strategy=Task Arithmetic, Quantization Method=None, Model Backbone=CLIP-ViT-B/32, Bit-width=Full2026.050.461——
Noun SubmanifoldBackbone=CLIP ViT-B-32, Evaluation Protocol=Zero-shot2023.050.447——
SLIPZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.030.429——
VLM BaselineIR=16, Backbone=VLM2026.010.414——
Simple Averaging w/ AWQMerging Strategy=Simple Averaging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.4121——
ITOZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.030.406——
Simple Averaging + E-PMQMerging Strategy=Simple Averaging, Quantization Method=E-PMQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.4039——
Simple Averaging + AWQMerging Strategy=Simple Averaging, Quantization Method=AWQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.4029——
Simple Averaging w/ RTNMerging Strategy=Simple Averaging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3991——
Simple Averaging + RTNMerging Strategy=Simple Averaging, Quantization Method=RTN, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3982——
TIES-Merging + E-PMQMerging Strategy=TIES-Merging, Quantization Method=E-PMQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3951——
Simple Averaging w/ E-PMQMerging Strategy=Simple Averaging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3951——
WUDI-Merging w/ E-PMQMerging Strategy=WUDI-Merging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3924——
WUDI-Merging + E-PMQMerging Strategy=WUDI-Merging, Quantization Method=E-PMQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3898——
TIES-Merging w/ E-PMQMerging Strategy=TIES-Merging, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.388——
Task Arithmetic w/ E-PMQMerging Strategy=Task Arithmetic, Quantization Method=E-PMQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3842——
WUDI-Merging w/ RTNMerging Strategy=WUDI-Merging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3831——
Simple Averaging + GPTQMerging Strategy=Simple Averaging, Quantization Method=GPTQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3809——
Simple Averaging w/ GPTQMerging Strategy=Simple Averaging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3802——
POS PGABackbone=CLIP ViT-B-32, Evaluation Protocol=Zero-shot2023.050.38——
Task Arithmetic + E-PMQMerging Strategy=Task Arithmetic, Quantization Method=E-PMQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3792——
WUDI-Merging w/ AWQMerging Strategy=WUDI-Merging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3781——
CLIPBackbone=CLIP ViT-B-32, Evaluation Protocol=Zero-shot2023.050.378——
TIES-Merging w/ AWQMerging Strategy=TIES-Merging, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3773——
POS PCABackbone=CLIP ViT-B-32, Evaluation Protocol=Zero-shot2023.050.376——
WUDI-Merging w/ GPTQMerging Strategy=WUDI-Merging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3752——
WUDI-Merging + RTNMerging Strategy=WUDI-Merging, Quantization Method=RTN, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3667——
CLIPZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.030.364——
WUDI-Merging + AWQMerging Strategy=WUDI-Merging, Quantization Method=AWQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3628——
WUDI-Merging + GPTQMerging Strategy=WUDI-Merging, Quantization Method=GPTQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3626——
POS PGABackbone=CLIP ViT-L-14, zero-shot=true2023.050.358——
CLIPBackbone=CLIP ViT-L-14, zero-shot=true2023.050.357——
POS PCABackbone=CLIP ViT-L-14, zero-shot=true2023.050.357——
TIES-Merging w/ RTNMerging Strategy=TIES-Merging, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3566——
Standard CLIPEvaluation Protocol=zero-shot2024.110.35——
Task ArithmeticMerging Strategy=Task Arithmetic, Quantization Method=Full-precision, Bit-width=Full, Backbone=CLIP-ViT-B/322026.050.343——
ITO sub2Backbone=ViT-L/16, Pre-training Dataset=DataComp-1B, Training Epochs=1, Evaluation Protocol=Zero-shot2026.030.337——
CLIPBackbone=ViT-L/16, Pre-training Dataset=DataComp-1B, Training Epochs=1, Evaluation Protocol=Zero-shot2026.030.336——
TIES-Merging + RTNMerging Strategy=TIES-Merging, Quantization Method=RTN, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.3282——
SLIPPre-training Dataset=CC12M, Backbone=ViT-B/16, Epochs=30, Evaluation protocol=Zero-shot2026.030.317——
Task Arithmetic w/ AWQMerging Strategy=Task Arithmetic, Quantization Method=AWQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3153——
ITOBackbone=ViT-L/16, Pre-training Dataset=DataComp-1B, Training Epochs=1, Evaluation Protocol=Zero-shot2026.030.314——
TIES-Merging w/ GPTQMerging Strategy=TIES-Merging, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3136——
Task Arithmetic w/ RTNMerging Strategy=Task Arithmetic, Quantization Method=RTN, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.3132——
TIES-Merging + AWQMerging Strategy=TIES-Merging, Quantization Method=AWQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.2983——
CLIPPre-training Dataset=CC12M, Backbone=ViT-B/16, Epochs=30, Evaluation protocol=Zero-shot2026.030.296——
Task Arithmetic w/ GPTQMerging Strategy=Task Arithmetic, Quantization Method=GPTQ, Model Backbone=CLIP-ViT-B/32, Bit-width=4-bit2026.050.2871——
CLIPPre-train dataset=CC3M, Backbone=ViT-B/16, Training Epochs=30, Evaluation Protocol=Zero-shot2026.030.273——
ITO sub2Pre-train dataset=CC3M, Backbone=ViT-B/16, Training Epochs=30, Evaluation Protocol=Zero-shot2026.030.269——
Task Arithmetic + RTNMerging Strategy=Task Arithmetic, Quantization Method=RTN, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.2685——
FLAIRPre-train dataset=CC3M, Backbone=ViT-B/16, Training Epochs=30, Evaluation Protocol=Zero-shot2026.030.268——
TIES-Merging + GPTQMerging Strategy=TIES-Merging, Quantization Method=GPTQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.2523——
Task Arithmetic + AWQMerging Strategy=Task Arithmetic, Quantization Method=AWQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.2492——
Task Arithmetic + GPTQMerging Strategy=Task Arithmetic, Quantization Method=GPTQ, Bit-width=4-bit, Backbone=CLIP-ViT-B/322026.050.2304——
B-cosified RN-50 CLIPPre-training Dataset=CC3M [47], Learning Scheduler=Cyclic, Evaluation Protocol=zero-shot2024.110.23——
FLAIRPre-training Dataset=CC12M, Backbone=ViT-B/16, Epochs=30, Evaluation protocol=Zero-shot2026.030.228——
ITOPre-train dataset=CC3M, Backbone=ViT-B/16, Training Epochs=30, Evaluation Protocol=Zero-shot2026.030.214——
B-cosified RN-50 CLIPPre-training Dataset=ImageNet [16], Learning Scheduler=Cosine, Evaluation Protocol=zero-shot2024.110.21——
SigLIPPre-training Dataset=CC12M, Backbone=ViT-B/16, Epochs=30, Evaluation protocol=Zero-shot2026.030.209——