Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/BLIP_ViT-L

BLIP_ViT-L

Reported on 8 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing8 results

Image Captioningonnocaps-val-out-domain
CIDEr· 2022-01-28
115.3
best: 124.8 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
SOTA
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation arXiv:2201.12086
Image Captioningonnocaps-val-out-domain
SPICE· 2022-01-28
14.4
best: 15.1 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
SOTA
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation arXiv:2201.12086
Image Captioningonnocaps-val-near-domain
CIDEr· 2022-01-28
112.1
best: 120.2 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation arXiv:2201.12086
Image Captioningonnocaps-val-near-domain
SPICE· 2022-01-28
14.9
best: 15.9 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation arXiv:2201.12086
Image Captioningonnocaps-val-overall
CIDEr· 2022-01-28
113.2
best: 121.6 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation arXiv:2201.12086
Image Captioningonnocaps-val-overall
SPICE· 2022-01-28
14.8
best: 15.8 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation arXiv:2201.12086
Image Captioningonnocaps-val-in-domain
CIDEr· 2022-01-28
114.9
best: 123.7 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation arXiv:2201.12086
Image Captioningonnocaps-val-in-domain
SPICE· 2022-01-28
15.2
best: 16.3 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation arXiv:2201.12086