AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, Dahua Lin

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 816 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace SFT detailed captions with GPT4-Vision captions (3.5% of SFT data) (ablation)LLaVA-1.5, Qwen-VL-Chat, LLaVA · MME and MMBenchMME / MMBench: MME +222.8/22.0/22.3; MMBench +2.7/1.3/1.5Improved
add ShareGPT4V captions in SFT only (ablation)LLaVA-1.5-7B · MME Perception / MMBench / SEEDMME Perception: 1510.7 -> 1542.1; MMBench 64.3 -> 66.8; SEED 66.2 -> 66.7Improved
add ShareGPT4V-PT captions in pre-training only (ablation)LLaVA-1.5-7B · MME Perception / MMBench / SEEDMME Perception: 1510.7 -> 1557.2; MMBench 64.3 -> 67.4; SEED 66.2 -> 68.5Improved
use ShareGPT4V in both pre-training and SFT (ablation)LLaVA-1.5-7B · MME Perception / MMBench / SEEDMME Perception: 1510.7 -> 1567.4; MMBench 64.3 -> 68.8; SEED 66.2 -> 69.7Improved
replace BLIP captions with ShareGPT4V-PT captions for the same 558K images (ablation)LLaVA-1.5-7B pre-training · MME Perception / MMBench / SEEDMME Perception: 1521.6 -> 1539.8; MMBench 66.2 -> 68.3; SEED 66.9 -> 68.9Improved
joint training with BLIP-558K captions (ablation)LLaVA-1.5-7B pre-training · MME Perception / SEEDMME Perception: 1516.9 -> 1521.6No clear effect
unfreeze latter half of vision encoder blocks during pre-training instead of freezing (ablation)ShareGPT4V-7B · MME Perception / MMBench / SEEDMME Perception: 1515.2 -> 1567.4Improved
unfreeze more vision blocks than latter half (blocks 6 or 0) (ablation)ShareGPT4V-7B · MME PerceptionMME Perception: 1567.4 -> 1529.5 (block 6); 1545.7 (block 0)Hurt
scale pre-training captions beyond 1000K (ablation)ShareGPT4V-7B pre-training · MMBench and SEEDaccuracyNo clear effect
Share-Captioner instead of GPT4-Vision for caption scaling (ablation)ShareGPT4V-PT generation · human preference over 100 samplespreference percentage: GPT4-Vision 38.2% vs Share-Captioner 35.3%No clear effect

Later papers that compared with this method

2 later accepted papers report ShareGPT4V-7B as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy