AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Towards Open-ended Visual Quality Comparison

Haoning Wu, Hanwei Zhu, Zicheng Zhang, Erli Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Annan Wang, Wenxiu Sun, Qiong Yan, Xiaohong Liu, Guangtao Zhai and 2 more

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 64 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
add multi-image comparative data (Merge2Compare and Teach2Compare) to single-image Q-Instruct training (ablation)mPLUG-Owl2 · Q-Bench PAIR-A1accuracy: 53.15 -> 80.18Improved
add comparative data (ablation)mPLUG-Owl2 · MICBenchaccuracy: 45.98 -> 83.33Improved
add Merge2Compare to Q-Instruct (ablation)mPLUG-Owl2 · Q-Bench PAIR-A1accuracy: 53.15 -> 68.67Improved
train with only GPT-4V labels (Teach2Compare) and no Merge2Compare (ablation)mPLUG-Owl2 · Q-Bench PAIR-A1accuracy: 78.28 vs GPT-4V 78.07No clear effect
combine hetero-sourced Merge2Compare with Teach2Compare (full) (ablation)mPLUG-Owl2 · MICBenchaccuracy: 76.41 -> 83.33Improved
use image-text interleaved format with ordinal labels instead of piling images (ablation)Co-Instruct · MICBenchaccuracy: 78.92 -> 83.33Improved
use learnable special image start/end tokens instead of ordinal text (ablation)Co-Instruct · MICBenchaccuracy: 83.33 -> 80.12Hurt
add top-similarity pair removal to Merge2Compare construction (ablation)Merge2Compare data · human check of 250 samplescorrectness rate: 72% -> 96%Improved
add comparative training data on single-image evaluation (ablation)mPLUG-Owl2 · Q-Bench SINGLE-A1accuracy: 73.38 -> 77.12Improved
Co-Instruct versus GPT-4V on detailed reasoning scoreCo-Instruct · Q-Bench PAIR-A2summed GPT score: 4.89 -> 4.82Hurt
extend context window for LMMs lacking visual token reduction on four imagesLLaVA, InternLM-XComposer2 · MICBenchaccuracy: 55.70 (three) -> 46.51 (four) for XComposer2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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