List your company

Scene Text Visual Question Answering on ST-VQA (test)

0.799ANLSPaLI-17B
0.470360.555680.6410.72632Aug 3, 2022Aug 10, 2022Aug 17, 2022Aug 24, 2022Aug 31, 2022Sep 7, 2022Sep 14, 2022

Evaluation results

MethodLinks
PaLI-17BVocabulary setting=Open-vocabulary generation2022.090.799—
PaLI-15BVocabulary setting=Open-vocabulary generation2022.090.765—
GIT2Parameters=5.1B, Vocabulary setting=Closed-vocabulary classification2022.090.758—
PaLI-3BVocabulary setting=Open-vocabulary generation2022.090.697—
GITParameters=0.7B, Vocabulary setting=Closed-vocabulary classification2022.090.696—
TAP + TAGExtra Data=TextVQA2022.080.602—
TAP††Extra Data=TextVQA, TextCaps, OCR-CC2022.080.597—
TAP + TAGExtra Data=None2022.080.586—
LOGOSExtra Data=TextVQA2022.080.579—
M4C⁺ + TAGExtra Data=TextVQA2022.080.571—
M4C†Extra Data=TextVQA2022.080.552—
SSBaselineExtra Data=TextVQA2022.080.55—
TAPExtra Data=None2022.080.543—
M4C⁺ + TAGExtra Data=None2022.080.529—
LOGOSExtra Data=None2022.080.522—
M4C†Extra Data=None2022.080.517—
SSBaselineExtra Data=None2022.080.509—
SA-M4CExtra Data=None2022.080.504—
SMAExtra Data=None2022.080.486—
LaAP-NetExtra Data=None2022.080.485—
CRNExtra Data=None2022.080.483—
DocPediaResolution=2560x2560, In-house data=false2024.03—45.5
InfiMM-HDResolution=dynamic, In-house data=false2024.03—67
MonkeyResolution=1344x768, In-house data=true2024.03—67.7
PaLI-3 (Specialist)OCR pipeline input=false, Model Category=Specialist, Reference Citation=[8]2023.12—84.1
PaLI-3 (Specialist)OCR pipeline input=true, Model Category=Specialist, Reference Citation=[8]2023.12—85.7
SMoLA-PaLI-3FTOCR pipeline input=false, Model Category=Generalist, Backbone=PaLI-32023.12—83.8
SMoLA-PaLI-3FTOCR pipeline input=true, Model Category=Generalist, Backbone=PaLI-32023.12—85.9
SMoLA-PaLI-XFTOCR pipeline input=false, Model Category=Generalist, Backbone=PaLI-X2023.12—78.9
SMoLA-PaLI-XFTOCR pipeline input=true, Model Category=Generalist, Backbone=PaLI-X2023.12—86
UniDocResolution=224x224, In-house data=false2024.03—30.8