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-2 ViT-G OPT 2.7B (zero-shot)

BLIP-2 ViT-G OPT 2.7B (zero-shot)

Reported on 14 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing14 results

Visual Question Answering (VQA)onOK-VQA
Accuracy· 2023-01-30
31.7
best: 66.8 (PaLI-X-VPD)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Visual Question Answering (VQA)onVQA v2 val
Accuracy· 2023-01-30
53.5
best: 82.19 (BLIP-2 ViT-G OPT 6.7B (fine-tuned))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Visual Question Answering (VQA)onGQA test-dev
Accuracy· 2023-01-30
34.6
best: 72.1 (CFR)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2023-01-30
52.3
best: 84.3 (PaLI)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image Captioningonnocaps-val-out-domain
CIDEr· 2023-01-30
123.4
best: 124.8 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image Captioningonnocaps-val-out-domain
SPICE· 2023-01-30
15.1
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image Captioningonnocaps-val-near-domain
CIDEr· 2023-01-30
117.8
best: 120.2 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image Captioningonnocaps-val-near-domain
SPICE· 2023-01-30
15.4
best: 15.9 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image CaptioningonCOCO Captions
BLEU-4· 2023-01-30
43.7
best: 46.5 (mPLUG)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image CaptioningonCOCO Captions
CIDER· 2023-01-30
145.8
best: 155.1 (mPLUG)
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image Captioningonnocaps-val-overall
CIDEr· 2023-01-30
119.7
best: 121.6 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image Captioningonnocaps-val-overall
SPICE· 2023-01-30
15.4
best: 15.8 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image Captioningonnocaps-val-in-domain
CIDEr· 2023-01-30
123
best: 123.7 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597
Image Captioningonnocaps-val-in-domain
SPICE· 2023-01-30
15.8
best: 16.3 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models arXiv:2301.12597