paper-with-me

Visual Question Answering 벤치마크

Visual Question Answering on VQA v2 test-dev

22개 결과 · ⬇ CSV · JSON

Accuracy

56.2 62.73 69.25 75.78 82.3 2021-11 2026-09 Florence — 80.16 (2021-11-22) Florence — 80.16 (2021-11-22) OFA — 82.0 (2022-02-07) OFA — 82.0 (2022-02-07) CoCa — 82.3 (2022-05-04) CoCa — 82.3 (2022-05-04) BLIP-2 ViT-G OPT 6.7B (fine-tuned) — 82.3 (2023-01-30) BLIP-2 ViT-G OPT 2.7B (fine-tuned) — 81.74 (2023-01-30) BLIP-2 ViT-G FlanT5 XL (fine-tuned) — 81.66 (2023-01-30) BLIP-2 ViT-G OPT 6.7B (fine-tuned) — 82.3 (2023-01-30) BLIP-2 ViT-G OPT 2.7B (fine-tuned) — 81.74 (2023-01-30) BLIP-2 ViT-G FlanT5 XL (fine-tuned) — 81.66 (2023-01-30) mPLUG-2 — 81.11 (2023-02-01) mPLUG-2 — 81.11 (2023-02-01) VK-OOD — 76.8 (2023-02-11) VK-OOD — 76.8 (2023-02-11) LXMERT (low-magnitude pruning) — 70.72 (2023-10-23) LXMERT (low-magnitude pruning) — 70.72 (2023-10-23) LocVLM-L — 56.2 (2024-04-11) LocVLM-L — 56.2 (2024-04-11) Florence — 80.16 (2021-11-22) OFA — 82.0 (2022-02-07) CoCa — 82.3 (2022-05-04)
RankModel Accuracy PaperCodeYear
1 BLIP-2 ViT-G OPT 6.7B (fine-tuned) 82.30 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models huggingface/transformers · salesforce/lavis · thudm/visualglm-6b · +14 2023
1 CoCa 82.3 CoCa: Contrastive Captioners are Image-Text Foundation Models mlfoundations/open_clip · facebookresearch/multimodal · lucidrains/CoCa-pytorch · +3 2022
3 OFA 82.0 OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework modelscope/modelscope · ofa-sys/ofa · JHKim-snu/GVCCI · +1 2022
4 BLIP-2 ViT-G OPT 2.7B (fine-tuned) 81.74 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models huggingface/transformers · salesforce/lavis · thudm/visualglm-6b · +14 2023
5 BLIP-2 ViT-G FlanT5 XL (fine-tuned) 81.66 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 mPLUG-2 81.11 mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video modelscope/modelscope · x-plug/mplug-owl · alibaba/AliceMind · +1 2023
7 Florence 80.16 Florence: A New Foundation Model for Computer Vision microsoft/unicl · MindCode-4/code-3 2021
8 Aurora (ours, r=64) 77.69
9 VK-OOD 76.8 Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis ellenzhuwang/VK_OOD 2023
10 LXMERT (low-magnitude pruning) 70.72 LXMERT Model Compression for Visual Question Answering ghazaleh-mahmoodi/lxmert_compression · pwc-1/Paper-9 2023
11 LocVLM-L 56.2 Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs kahnchana/locvlm 2024
12 BLIP-2 ViT-G OPT 6.7B (fine-tuned) 82.30 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models huggingface/transformers · salesforce/lavis · thudm/visualglm-6b · +14 2023
12 CoCa 82.3 CoCa: Contrastive Captioners are Image-Text Foundation Models mlfoundations/open_clip · facebookresearch/multimodal · lucidrains/CoCa-pytorch · +3 2022
14 OFA 82.0 OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework modelscope/modelscope · ofa-sys/ofa · JHKim-snu/GVCCI · +1 2022
15 BLIP-2 ViT-G OPT 2.7B (fine-tuned) 81.74 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models huggingface/transformers · salesforce/lavis · thudm/visualglm-6b · +14 2023
16 BLIP-2 ViT-G FlanT5 XL (fine-tuned) 81.66 BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models huggingface/transformers · salesforce/lavis · thudm/visualglm-6b · +14 2023
17 mPLUG-2 81.11 mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video modelscope/modelscope · x-plug/mplug-owl · alibaba/AliceMind · +1 2023
18 Florence 80.16 Florence: A New Foundation Model for Computer Vision microsoft/unicl · MindCode-4/code-3 2021
19 Aurora (ours, r=64) 77.69
20 VK-OOD 76.8 Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis ellenzhuwang/VK_OOD 2023
1–20 / 22 다음 → 페이지당 10 20 50 100