List your company

Image Captioning on NoCaps (Domain Breakdown Evaluation)

111.3CIDEr (in-domain)BLIP
32.2652.7873.393.82Sep 15, 2022Mar 29, 2023Oct 11, 2023Apr 24, 2024Nov 6, 2024May 21, 2025Dec 3, 2025

Evaluation results

MethodLinks
BLIP# Img-Text Pairs=14M2022.09111.315.1104.514.4102.413.7105.114.4
OmniVL# Img-Text Pairs=14M*2022.09104.615108.314.9106.314.2107.514.7
LEMON# Img-Text Pairs=12M2022.09104.514.6100.71496.712.4100.413.8
VinVL# Img-Text Pairs=5.7M2022.09103.114.296.113.888.312.195.513.5
sample-kk=4, Datastore=+Web2024.0694.8—89.5—93.1———
c-sample-kk=4, Datastore=+Web2024.0694.5—90—93.3———
top-kk=4, Datastore=+Web2024.0694.2—89.4—91.2———
sample-kk=3, Datastore=+Web2024.0692.6—88—90———
Enc-Dec# Img-Text Pairs=15M2022.0992.612.588.312.194.511.990.212.1
top-kk=3, Datastore=+Web2024.0691.7—88.3—89.9———
sample-kk=2, Datastore=+Web2024.0690.6—85.3—86.7———
top-kk=2, Datastore=+Web2024.0690.5—86.2—89.5———
c-sample-kk=4, Datastore=Standard2024.0690.1—81.3—71.5———
sample-kk=4, Datastore=Standard2024.0689.7—80.9—71.1———
sample-kk=3, Datastore=Standard2024.0688.7—80.3—69.4———
sample-kk=2, Datastore=Standard2024.0687.8—77.4—67.6———
sample-kk=1, Datastore=+Web2024.0687.8—81.2—77.5———
top-kk=3, Datastore=Standard2024.0687.4—79.6—68.3———
top-kk=4, Datastore=Standard2024.0687.4—79.6—68.3———
sample-kk=1, Datastore=Standard2024.0687—75.7—63.6———
top-kk=1, Datastore=Standard2024.0685—74.3—62.3———
top-kk=2, Datastore=Standard2024.0685—74.3—62.3———
top-kk=1, Datastore=+Web2024.0684.1—80.7—81.5———
TipCapEncoder=ViT-L/14, Decoder=GPT2-large2025.1280.2—62.3—39.6—60.3—
TOMCap (large)Encoder=ViT-L/16, Decoder=GPT2-large2025.1277.1—76.6—75.9—76.4—
TOMCapEncoder=ViT-L/16, Decoder=GPT2-base2025.1276.3—75.5—75.7—76.2—
IFCapEncoder=ViT-B/32, Decoder=GPT2-base2025.1270.1—72.5—72.1—74—
CapDec+RLCF-SEncoder=ViT-B/16, Decoder=OPT-125M2025.1268.3—58.5—35.3———
ViECap+ToCaEncoder=ViT-B/32, Decoder=GPT2-base2025.1264.6—69.1—70.5—70.9—
EntroCapEncoder=ViT-B/32, Decoder=GPT2-base2025.1262.5—64.5—67.5—67—
ViECapEncoder=ViT-B/32, Decoder=GPT2-base2025.1261.1—64.3—65—66.2—
CapDecEncoder=ResNet50, Decoder=GPT2-large2025.1260.1—50.2—28.7—45.9—
ICSDEncoder=ViT-B/32, Decoder=BERT-base2025.1242.9—44.3—35.6—42.7—
DeCapEncoder=ViT-B/32, Decoder=Transformer2025.1241.9—41.7—46.2—42.7—
MeaCapToTEncoder=ViT-B/32, Decoder=CBART2025.1238.5—43.6—50—45.1—
MeaCapTFEncoder=ViT-B/32, Decoder=CBART2025.1235.3—39—45.1—40.2—
SIMVLM# Img-Text Pairs=1.8B2022.09——————94.813.1