AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Foundation Model is Efficient Multimodal Multitask Model Selector

Fanqing Meng, Wenqi Shao, zhanglin peng, Chonghe Jiang, Kaipeng Zhang, Yu Qiao, Ping Luo

NeurIPS 2023 · Vision-language and multimodal › Visual question answering · approach: Multimodal LLM question answering · 4 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
increase number of F-Labels K from 1 to 3 (ablation)EMMS · Flickr8k captioningweighted Kendall tau: 0.490 -> 0.660Improved
increase K from 3 to 4 (ablation)EMMS · FlickrStyle10K-Romantic captioningweighted Kendall tau: 0.678 -> 0.644Hurt
increase K from 3 to 4 (ablation)EMMS · Flickr8k captioningweighted Kendall tau: 0.660 -> 0.660No clear effect
reduce alternating-minimization iterations r from 3 to 1 (ablation)EMMS · DAQUAR VQAweighted Kendall tau: 0.743 -> 0.712No clear effect
reduce iterations r from 3 to 1 (ablation)EMMS · CLEVR VQAwall-clock time (s): 745.11 -> 274.56Improved
use CLIP-L instead of CLIP-B for F-Label (ablation)EMMS · FlickrStyle10K-Humor captioningweighted Kendall tau: 0.480 -> 0.802Improved
replace one-hot label with F-Label (ablation)EMMS · CNN image classification avgweighted Kendall tau: 0.618 -> 0.664Improved
replace one-hot label with F-Label (ablation)EMMS · ViT image classification avgweighted Kendall tau: 0.611 -> 0.639Improved
replace one-hot label with F-Label (ablation)EMMS · CNN image classification avgwall-clock time (s): 42.99 -> 143.2Hurt
combine three foundation models instead of single GPT-2 (ablation)EMMS · image classification avgweighted Kendall tau: 0.610 -> 0.639Improved
combine three foundation models instead of single GPT-2 (ablation)EMMS · image captioning avgweighted Kendall tau: 0.545 -> 0.670Improved
combine three foundation models instead of CLIP alone (ablation)EMMS · image captioning avgweighted Kendall tau: 0.628 -> 0.670Improved

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