AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Parameter-efficient Tuning of Large-scale Multimodal Foundation Model

Haixin Wang, Xinlong Yang, Jianlong Chang, Dian Jin, Jinan Sun, Shikun Zhang, Xiao Luo, Qi Tian

NeurIPS 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Parameter-efficient visual tuning · 5 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
remove informative context enhancement (Aurora w/o C) (ablation)Aurora · Flickr30K / DiDemo / MSCOCOrecallHurt
replace context with random vectors (Aurora w. R) (ablation)Aurora · cross-modal retrievalrecallHurt
use uniform average of queries instead of adaptive weights (Aurora w. M) (ablation)Aurora · cross-modal retrievalrecallHurt
remove gated query transformation (Aurora w/o Q) (ablation)Aurora · MSCOCO / DiDemorecallHurt
initialize gated transformation with ones instead of zeros (Aurora w. O) (ablation)Aurora · MSCOCO / DiDemorecallHurt
share parameters across multimodal encoder layers (ablation)Aurora · FLICKR30Krecall: average improvement of 0.1Improved
increase CP decomposition rank R (ablation)Aurora · Flickr30K / DiDemorecallImproved
increase rank from r=64 to r=128 (ablation)Aurora · MSCOCO I->TR@1: 80.2 -> 80.7Improved
increase rank from r=64 to r=128 (ablation)Aurora · FLICKR30K I->TR@1: 96.8 -> 97.2Improved
Aurora r=64 instead of UniAdapter r=512 on video retrievalUniAdapter (r=512) · MSR-VTTR@1: 50.6 -> 52.4Improved
Aurora r=64 instead of UniAdapter r=512 on VQAv2 test-devUniAdapter (r=512) · VQAv2 test-devaccuracy: 75.44 -> 77.69Improved
Aurora r=64 instead of LoRA in zero-shot retrievalBLIP + LoRA · DiDemo zero-shotR@1: 43.4 -> 44.6Improved

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