paper-with-me

Generative Visual Question Answering 벤치마크

Generative Visual Question Answering on PMC-VQA

6개 결과 · ⬇ CSV · JSON

BLEU-1

4.1 8.875 13.65 18.43 23.2 2022-04 2026-09 Open-Flamingo — 4.1 (2022-04-29) Open-Flamingo — 4.1 (2022-04-29) BLIP-2 — 7.6 (2023-01-30) BLIP-2 — 7.6 (2023-01-30) MedVInT — 23.2 (2023-05-17) MedVInT — 23.2 (2023-05-17) Open-Flamingo — 4.1 (2022-04-29) BLIP-2 — 7.6 (2023-01-30) MedVInT — 23.2 (2023-05-17)
RankModel BLEU-1 PaperCodeYear
1 MedVInT 23.2 PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering xiaoman-zhang/PMC-VQA · zihanzhaosjtu/librisqa 2023
2 BLIP-2 7.6 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models huggingface/transformers · salesforce/lavis · thudm/visualglm-6b · +14 2023
3 Open-Flamingo 4.1 Flamingo: a Visual Language Model for Few-Shot Learning mlfoundations/open_flamingo · lucidrains/flamingo-pytorch · unispac/visual-adversarial-examples-jailbreak-large-language-models · +2 2022
4 MedVInT 23.2 PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering xiaoman-zhang/PMC-VQA · zihanzhaosjtu/librisqa 2023
5 BLIP-2 7.6 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models huggingface/transformers · salesforce/lavis · thudm/visualglm-6b · +14 2023
6 Open-Flamingo 4.1 Flamingo: a Visual Language Model for Few-Shot Learning mlfoundations/open_flamingo · lucidrains/flamingo-pytorch · unispac/visual-adversarial-examples-jailbreak-large-language-models · +2 2022
1–6 / 6 페이지당 10 20 50 100