List your company

Image Classification on ImageNet-1K (val) (Top-1 and Top-5 Accuracy)

86.22Top-1 AccuracyFiPS + FT
76.49679.020581.54584.0695Dec 27, 2021Jun 20, 2022Dec 13, 2022Jun 6, 2023Nov 29, 2023May 22, 2024Nov 14, 2024

Evaluation results

MethodLinks
FiPS + FTModel=Swin-L, Parameter Budget=75%, Compression Ratio=∼6%2024.1186.22—
FiPSModel=Swin-L, Parameter Budget=75%, Compression Ratio=∼6%2024.1186.21—
GFMModel=Swin-L, Parameter Budget=75%, Compression Ratio=∼6%2024.1186.01—
FiPSModel=Swin-L, Parameter Budget=50%, Compression Ratio=∼25%2024.1185.99—
FiPS + FTModel=Swin-L, Parameter Budget=50%, Compression Ratio=∼25%2024.1185.99—
AAFMModel=Swin-L, Parameter Budget=75%, Compression Ratio=∼6%2024.1185.94—
FiPSModel=Swin-L, Parameter Budget=40%, Compression Ratio=∼33%2024.1185.69—
FiPS + FTModel=Swin-L, Parameter Budget=40%, Compression Ratio=∼33%2024.1185.68—
GFMModel=Swin-L, Parameter Budget=50%, Compression Ratio=∼25%2024.1185.44—
FiPS + FTModel=Swin-L, Parameter Budget=25%, Compression Ratio=∼45%2024.1185.16—
AAFMModel=Swin-L, Parameter Budget=50%, Compression Ratio=∼25%2024.1185.04—
FiPSModel=Swin-L, Parameter Budget=25%, Compression Ratio=∼45%2024.1184.78—
Baseline/512Model family=LV-VIT-M, Params (M)=55.83, GFLOPS=12.67, GFLOPs↓ (%)=0.00, Embedding dimensions=5122021.1284—
DynamicViTModel family=LV-VIT-M, Params (M)=57.10, GFLOPS=8.45, GFLOPs↓ (%)=33.312021.1283.8—
SPVITModel family=LV-VIT-M, Params (M)=55.85, GFLOPS=7.32, GFLOPs↓ (%)=42.232021.1283.71—
DynamicViTModel family=LV-VIT-M, Params (M)=57.10, GFLOPS=7.35, GFLOPs↓ (%)=41.99, Reproduced=true2021.1283.61—
Baseline/384Model family=LV-VIT-S, Params (M)=26.15, GFLOPS=6.55, GFLOPs↓ (%)=0.00, Embedding dimensions=3842021.1283.3—
Swin-BModel family=LV-VIT-M, Params (M)=88.00, GFLOPS=15.40, GFLOPs↓ (%)=-21.552021.1283.3—
CvT-21/384Model family=LV-VIT-M, Params (M)=32.00, GFLOPS=24.90, GFLOPs↓ (%)=-96.532021.1283.3—
SPVITModel family=LV-VIT-S, Params (M)=26.17, GFLOPS=4.28, GFLOPs↓ (%)=34.652021.1283.1—
ATS+CVT-21/384Model family=LV-VIT-M, Params (M)=32.00, GFLOPS=17.40, GFLOPs↓ (%)=-37.332021.1283.1—
DynamicViTModel family=LV-VIT-S, Params (M)=26.90, GFLOPS=4.57, GFLOPs↓ (%)=30.222021.1283—
Swin-SModel family=LV-VIT-M, Params (M)=50.00, GFLOPS=8.70, GFLOPs↓ (%)=31.332021.1283—
CvT-13/384Model family=LV-VIT-M, Params (M)=20.00, GFLOPS=16.30, GFLOPs↓ (%)=-28.652021.1283—
ATS+CVT-13/384Model family=LV-VIT-M, Params (M)=20.00, GFLOPS=11.70, GFLOPs↓ (%)=7.662021.1282.9—
RegNetY-16GModel family=LV-VIT-M, Params (M)=84.00, GFLOPS=16.00, GFLOPs↓ (%)=-26.282021.1282.9—
TNT-BModel family=LV-VIT-M, Params (M)=66.00, GFLOPS=14.10, GFLOPs↓ (%)=-11.292021.1282.8—
CvT-21/224Model family=LV-VIT-M, Params (M)=32.00, GFLOPS=7.10, GFLOPs↓ (%)=43.962021.1282.5—
ATS+CVT-21Model family=LV-VIT-S, Params (M)=32.00, GFLOPS=5.10, GFLOPs↓ (%)=22.142021.1282.3—
T2T-ViT-24Model family=LV-VIT-M, Params (M)=64.10, GFLOPS=14.10, GFLOPs↓ (%)=-11.292021.1282.3—
DHVT-S#Params=24.1M, Image Size=224, GFLOPs=4.7, Initialization=random2022.1082.3—
CrossViT-BModel family=LV-VIT-M, Params (M)=104.70, GFLOPS=21.20, GFLOPs↓ (%)=-67.322021.1282.2—
Focal-T#Params=29.1M, Image Size=224, GFLOPs=4.9, Initialization=random2022.1082.2—
FiPS + FTModel=Swin-L, Parameter Budget=10%, Compression Ratio=∼57%2024.1182.13—
ConvNeXt-T#Params=29M, Image Size=224, GFLOPs=4.5, Initialization=random2022.1082.1—
LG-T#Params=32.6M, Image Size=224, GFLOPs=4.8, Initialization=random2022.1082.1—
CeiT-S#Params=24.2M, Image Size=224, GFLOPs=4.5, Initialization=random2022.1082—
ViL-S#Params=24.6M, Image Size=224, GFLOPs=4.9, Initialization=random2022.1082—
PVTv2-B2#Params=25.4M, Image Size=224, GFLOPs=4.0, Initialization=random2022.1082—
VITAE-S#Params=23.6M, Image Size=224, GFLOPs=5.6, Initialization=random2022.1082—
T2T-ViT-19Model family=LV-VIT-M, Params (M)=39.20, GFLOPS=8.90, GFLOPs↓ (%)=29.762021.1281.9—
CoaT-Lite Small#Params=20.0M, Image Size=224, GFLOPs=4.0, Initialization=random2022.1081.9—
GFMModel=DeiT-B, Parameter Budget=75%, Compression Ratio=∼6%2024.1181.83—
FiPSModel=DeiT-B, Parameter Budget=50%, Compression Ratio=∼25%2024.1181.83—
FiPSModel=DeiT-B, Parameter Budget=75%, Compression Ratio=∼6%2024.1181.82—
FiPS + FTModel=DeiT-B, Parameter Budget=75%, Compression Ratio=∼6%2024.1181.82—
DeiT-BModel family=LV-VIT-M, Params (M)=86.60, GFLOPS=17.60, GFLOPs↓ (%)=-38.912021.1281.8—
CaiT-XS24#Params=26.6M, Image Size=224, GFLOPs=5.4, Initialization=random2022.1081.8—
AAFMModel=DeiT-B, Parameter Budget=75%, Compression Ratio=∼6%2024.1181.76—
RegNetY-8GModel family=LV-VIT-M, Params (M)=39.00, GFLOPS=8.00, GFLOPs↓ (%)=36.862021.1281.7—
Twins-SVT-S#Params=24.0M, Image Size=224, GFLOPs=2.8, Initialization=random2022.1081.7—
FiPSModel=DeiT-B, Parameter Budget=40%, Compression Ratio=∼33%2024.1181.69—
GFMModel=DeiT-B, Parameter Budget=50%, Compression Ratio=∼25%2024.1181.62—
CvT-13/224Model family=LV-VIT-S, Params (M)=20.00, GFLOPS=4.50, GFLOPs↓ (%)=31.292021.1281.6—
CvT-13#Params=20.0M, Image Size=224, GFLOPs=4.5, Initialization=random2022.1081.6—
FiPS + FTModel=DeiT-B, Parameter Budget=40%, Compression Ratio=∼33%2024.1181.54—
FiPS + FTModel=DeiT-B, Parameter Budget=50%, Compression Ratio=∼25%2024.1181.54—
CPVT-Small-GAPModel family=LV-VIT-S, Params (M)=23.00, GFLOPS=4.60, GFLOPs↓ (%)=29.772021.1281.5—
T2T-ViT-14Model family=LV-VIT-S, Params (M)=22.00, GFLOPS=5.20, GFLOPs↓ (%)=20.612021.1281.5—
T2T-ViT-14#Params=21.5M, Image Size=224, GFLOPs=5.2, Initialization=random2022.1081.5—
NesT-T#Params=17.0M, Image Size=224, GFLOPs=5.8, Initialization=random2022.1081.5—
MD-DeiT-SModel family=LV-VIT-S, Params (M)=22.10, GFLOPS=4.60, GFLOPs↓ (%)=29.772021.1281.48—
FiPS + FTModel=DeiT-B, Parameter Budget=25%, Compression Ratio=∼45%2024.1181.31—
Swin-TModel family=LV-VIT-S, Params (M)=29.00, GFLOPS=4.50, GFLOPs↓ (%)=31.292021.1281.3—
Conformer-Ti#Params=23.5M, Image Size=224, GFLOPs=5.2, Initialization=random2022.1081.3—
Swin-T#Params=29.0M, Image Size=224, GFLOPs=4.5, Initialization=random2022.1081.3—
ConViT-S#Params=27.8M, Image Size=224, GFLOPs=5.4, Initialization=random2022.1081.3—
TNT-S#Params=23.8M, Image Size=224, GFLOPs=5.2, Initialization=random2022.1081.3—
GFMModel=DeiT-B, Parameter Budget=40%, Compression Ratio=∼33%2024.1181.28—
NVIT-SModel family=LV-VIT-S, Params (M)=23.00, GFLOPS=4.70, GFLOPs↓ (%)=28.242021.1281.22—
AAFMModel=DeiT-B, Parameter Budget=50%, Compression Ratio=∼25%2024.1181.21—
PVT-MediumModel family=LV-VIT-S, Params (M)=44.20, GFLOPS=6.70, GFLOPs↓ (%)=-2.292021.1281.2—
PVT-Medium#Params=44.2M, Image Size=224, GFLOPs=6.7, Initialization=random2022.1081.2—
Evo-ViTModel family=LV-VIT-M, Params (M)=87.30, GFLOPS=9.07, GFLOPs↓ (%)=28.412021.1281.11—
CrossViT-SModel family=LV-VIT-S, Params (M)=26.70, GFLOPS=5.60, GFLOPs↓ (%)=14.502021.1281—
CrossViT-S#Params=26.7M, Image Size=224, GFLOPs=5.6, Initialization=random2022.1081—
PiT-S#Params=23.5M, Image Size=224, GFLOPs=2.9, Initialization=random2022.1080.9—
CoaT MiniModel family=LV-VIT-S, Params (M)=10.00, GFLOPS=6.80, GFLOPs↓ (%)=-3.822021.1280.8—
VTPModel family=LV-VIT-M, Params (M)=48.00, GFLOPS=10.00, GFLOPs↓ (%)=21.072021.1280.7—
FiPSModel=DeiT-B, Parameter Budget=25%, Compression Ratio=∼45%2024.1180.64—
AAFMModel=DeiT-B, Parameter Budget=40%, Compression Ratio=∼33%2024.1180.33—
Baseline/384Model family=DeiT-S, Params (M)=22.10, GFLOPS=4.60, GFLOPs↓ (%)=0.00, Embedding dimensions=3842021.1279.8—
SPVITModel family=DeiT-S, Params (M)=22.13, GFLOPS=3.86, GFLOPs↓ (%)=16.092021.1279.8—
DeiT-S#Params=22.1M, Image Size=224, GFLOPs=4.3, Initialization=random2022.1079.8—
PVT-S#Params=24.5M, Image Size=224, GFLOPs=3.8, Initialization=random2022.1079.8—
RegNetY-4.0GF#Params=20.6M, Image Size=224, GFLOPs=4.0, Initialization=random2022.1079.4—
SPVITModel family=DeiT-S, Params (M)=22.13, GFLOPS=2.64, GFLOPs↓ (%)=42.612021.1279.34—
DynamicViTModel family=DeiT-S, Params (M)=22.80, GFLOPS=2.91, GFLOPs↓ (%)=36.742021.1279.3—
S2VITEModel family=DeiT-S, Params (M)=14.60, GFLOPS=3.14, GFLOPs↓ (%)=31.742021.1279.22—
DynamicViTModel family=DeiT-S, Params (M)=22.80, GFLOPS=2.71, GFLOPs↓ (%)=41.09, Reproduced=true2021.1279.12—
IA-RED2Model family=DeiT-S, GFLOPS=3.15, GFLOPs↓ (%)=31.522021.1279.1—
Baseline/320Model family=DeiT-S, Params (M)=15.40, GFLOPS=3.25, GFLOPs↓ (%)=29.35, Embedding dimensions=320, Reproduced=true2021.1279—
SPVIT-320Model family=DeiT-S, Params (M)=15.44, GFLOPS=2.00, GFLOPs↓ (%)=56.52, Pruning source=DeiT scaling model of 320 embedding dimensions2021.1278.65—
Baseline/288Model family=DeiT-S, Params (M)=12.60, GFLOPS=2.65, GFLOPs↓ (%)=42.39, Embedding dimensions=288, Reproduced=true2021.1278.53—
HVT-S-1Model family=DeiT-S, Params (M)=22.10, GFLOPS=2.40, GFLOPs↓ (%)=47.822021.1278—
FiPS + FTModel=DeiT-B, Parameter Budget=10%, Compression Ratio=∼57%2024.1177.26—
Baseline/256Model family=DeiT-S, Params (M)=10.00, GFLOPS=2.14, GFLOPs↓ (%)=53.48, Embedding dimensions=256, Reproduced=true2021.1277.21—
SPVIT-320Model family=DeiT-T, Params (M)=15.44, GFLOPS=1.30, GFLOPs↓ (%)=0.00, Pruning source=DeiT scaling model of 320 embedding dimensions2021.1277.02—
ATS+DeiT/258Model family=DeiT-T, Params (M)=10.13, GFLOPS=1.50, GFLOPs↓ (%)=-15.382021.1276.9—
SPVIT-256Model family=DeiT-T, Params (M)=10.16, GFLOPS=1.29, GFLOPs↓ (%)=0.77, Pruning source=DeiT scaling model of 256 embedding dimensions2021.1276.87—