List your company
ResearchFormerly WizWand

Zero-shot Image Classification on ImageNet shift

69.6AccuracyEnsemble Teacher
42.5649.5856.663.62Nov 28, 2023
Updated 8mo ago

Evaluation results

MethodLinks
Ensemble TeacherTraining Dataset=DataComp-1B [18], OpenAI-400M [47], Image Encoder=ViT-L/14, Text Encoder=Base2023.1169.6
MobileCLIP-B (LT)Training Dataset=DataCompDR-1B, Seen Samples=39B, Image Encoder=ViT-B/16, Text Encoder=Base, Params (M)=86.3 + 63.4, Latency (ms)=10.4 + 3.32023.1166.1
MobileCLIP-BTraining Dataset=DataCompDR-1B, Seen Samples=13B, Image Encoder=ViT-B/16, Text Encoder=Base, Params (M)=86.3 + 63.4, Latency (ms)=10.4 + 3.32023.1165.6
MobileCLIP-S2Training Dataset=DataCompDR-1B, Seen Samples=13B, Image Encoder=MCi2, Text Encoder=Base, Params (M)=35.7 + 63.4, Latency (ms)=3.6 + 3.32023.1163.1
DFN-B/16Training Dataset=DFN-2B [16], Seen Samples=13B, Image Encoder=ViT-B/16, Text Encoder=Base, Params (M)=86.2 + 63.4, Latency (ms)=11.5 + 3.32023.1162.3
SigLIP-B/16Training Dataset=Webli-1B, Seen Samples=40B, Image Encoder=ViT-B/16, Text Encoder=Custom, Params (M)=92.9 + 110.3, Latency (ms)=9.9 + 5.82023.1161
DataComp-B/16Training Dataset=DataComp-1B [18], Seen Samples=13B, Image Encoder=ViT-B/16, Text Encoder=Base, Params (M)=86.2 + 63.4, Latency (ms)=11.5 + 3.32023.1160.8
MobileCLIP-S1Training Dataset=DataCompDR-1B, Seen Samples=13B, Image Encoder=MCi1, Text Encoder=Base, Params (M)=21.5 + 63.4, Latency (ms)=2.5 + 3.32023.1160.7
EVA02-B/16Training Dataset=Merged-2B [55], Seen Samples=8B, Image Encoder=ViT-B/16, Text Encoder=Base, Params (M)=86.2 + 63.42023.1159.6
DataComp-B/32-256Training Dataset=DataComp-1B [18], Seen Samples=34B, Image Encoder=ViT-B/32-256, Text Encoder=Base, Params (M)=86.2 + 63.4, Latency (ms)=6.2 + 3.32023.1158.7
LAION-B/16Training Dataset=LAION-2B [52], Seen Samples=34B, Image Encoder=ViT-B/16, Text Encoder=Base, Params (M)=86.2 + 63.4, Latency (ms)=11.5 + 3.32023.1156.6
OpenAI-B/16Training Dataset=WIT-400M [47], Seen Samples=13B, Image Encoder=ViT-B/16, Text Encoder=Base, Params (M)=86.2 + 63.4, Latency (ms)=11.5 + 3.32023.1155.9
DataComp-B/32Training Dataset=DataComp-1B [18], Seen Samples=13B, Image Encoder=ViT-B/32, Text Encoder=Base, Params (M)=86.2 + 63.4, Latency (ms)=5.9 + 3.32023.1155.2
MobileCLIP-S0Training Dataset=DataCompDR-1B, Seen Samples=13B, Image Encoder=MCi0, Text Encoder=MCt, Params (M)=11.4 + 42.4, Latency (ms)=1.5 + 1.62023.1155.1
LAION-B/32Training Dataset=LAION-2B [52], Seen Samples=32B, Image Encoder=ViT-B/32, Text Encoder=Base, Params (M)=86.2 + 63.4, Latency (ms)=5.9 + 3.32023.1151.9
TinyCLIP-61M/32Training Dataset=LAION-400M [51], Seen Samples=15.2B, Image Encoder=ViT-61M/32, Text Encoder=Custom, Params (M)=61.4 + 54.0, Latency (ms)=4.3 + 2.62023.1148.7
OpenAI-RN101Training Dataset=OpenAI-400M [47], Seen Samples=13B, Image Encoder=ResNet-101, Text Encoder=Base, Params (M)=56.3 + 63.4, Latency (ms)=4.3 + 3.32023.1148.5
OpenAI-B/32Training Dataset=OpenAI-400M [47], Seen Samples=13B, Image Encoder=ViT-B/32, Text Encoder=Base, Params (M)=86.2 + 63.4, Latency (ms)=5.9 + 3.32023.1148.5
TinyCLIP-40M/32Training Dataset=LAION-400M [51], Seen Samples=15.2B, Image Encoder=ViT-40M/32, Text Encoder=Custom, Params (M)=39.7 + 44.5, Latency (ms)=3.0 + 1.92023.1146.5
TinyCLIP-RN30MTraining Dataset=LAION-400M [51], Seen Samples=15.2B, Image Encoder=ResNet-30M, Text Encoder=Custom, Params (M)=29.6 + 54.2, Latency (ms)=2.6 + 2.62023.1145.7
OpenAI-RN50Training Dataset=OpenAI-400M [47], Seen Samples=13B, Image Encoder=ResNet-50, Text Encoder=Base, Params (M)=38.3 + 63.4, Latency (ms)=3.3 + 3.32023.1145.1
TinyCLIP-RN19MTraining Dataset=LAION-400M [51], Seen Samples=15.2B, Image Encoder=ResNet-19M, Text Encoder=Custom, Params (M)=18.6 + 44.8, Latency (ms)=1.9 + 1.92023.1143.6