List your company
ResearchFormerly WizWand

Image Captioning on COCO (test) (CIDEr Metric)

149.2CIDErPALI-X-55B
76.60895.454114.3133.146Jul 11, 2023Aug 29, 2023Oct 18, 2023Dec 6, 2023Jan 25, 2024Mar 14, 2024May 3, 2024
Updated 8mo ago

Evaluation results

MethodLinks
PALI-X-55Bmode=per-task finetuning2023.07149.2
PerceptionGPT2023.11123.2
Unified-IO2023.11122.1
Emu-Izero-shot=true, instruction_tuned=true2023.07120.4
Shikra2023.11117.5
MM1Size=7B, Architecture=fully autoregressive, # tokens per image=144, Few-shot=8 random in-context examples2024.05116.3
Idefics2-baseSize=8B, Architecture=fully autoregressive, # tokens per image=64, Few-shot=8 random in-context examples2024.05116
VPGTrans2023.11114.2
Emuzero-shot=true, prompt_strategy=Chain-of-Thought2023.07112.4
FlamingoSize=9B, Architecture=cross-attention, Few-shot=8 random in-context examples2024.0599
Idefics1Size=9B, Architecture=cross-attention, Few-shot=8 random in-context examples2024.0597
OpenFlamingoSize=9B, Architecture=cross-attention, Few-shot=8 random in-context examples2024.0596.3
Kosmos-12023.1184.7
Kosmos-1zero-shot=true2023.0784.7
FM-80B2023.1184.3
MetaLMzero-shot=true2023.0782.2
FM-9B2023.1179.4
Flamingo-9Bzero-shot=true, prompt_strategy=2-example text-only prompt2023.0779.4