TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Natural Language Processing/Image Captioning/nocaps-val-out-domain

Image Captioning on nocaps-val-out-domain

Metric: SPICE (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕SPICE▼Extra DataPaperDate↕Code
1BLIP-2 ViT-G FlanT5 XL (zero-shot)15.1NoBLIP-2: Bootstrapping Language-Image Pre-trainin...2023-01-30Code
2BLIP-2 ViT-G OPT 2.7B (zero-shot)15.1NoBLIP-2: Bootstrapping Language-Image Pre-trainin...2023-01-30Code
3BLIP-2 ViT-G OPT 6.7B (zero-shot)14.8NoBLIP-2: Bootstrapping Language-Image Pre-trainin...2023-01-30Code
4BLIP_ViT-L14.4NoBLIP: Bootstrapping Language-Image Pre-training ...2022-01-28Code
5BLIP_CapFilt-L14.2NoBLIP: Bootstrapping Language-Image Pre-training ...2022-01-28Code
6OmniVL14.2NoOmniVL:One Foundation Model for Image-Language a...2022-09-15-
7LEMON_large14NoScaling Up Vision-Language Pre-training for Imag...2021-11-24-
8VinVL12.1NoVinVL: Revisiting Visual Representations in Visi...2021-01-02Code
9Enc-Dec11.9NoConceptual 12M: Pushing Web-Scale Image-Text Pre...2021-02-17Code