AI Paper Atlas

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

Quantized Prompt for Efficient Generalization of Vision-Language Models

Tianxiang Hao, Xiaohan Ding, Juexiao Feng, Yuhong Yang, Hui Chen, Guiguang Ding

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 9 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 moderate Gaussian noise to prompts (not too small or large) (ablation)prompt tuning (CoOp) · Base-to-newnew-class accuracyImproved
quantize prompts with K-Means QAT (QCoOp) instead of fp16 CoOpCoOp · Base-to-new (11 datasets avg)harmonic mean: 71.66 -> 77.43Improved
quantize MaPLe prompts and linear weights (QMaPLe)MaPLe · Base-to-new (11 datasets avg)harmonic mean: 78.55 -> 79.12Improved
add normalization/denormalization before K-Means quantization (ablation)QCoOp · Base-to-newharmonic mean: 75.50 -> 75.85Improved
add constrained adaptive clustering (ablation)QCoOp · Base-to-newharmonic mean: 75.85 -> 76.07Improved
use QAT instead of PTQ for 1-bit quantization (ablation)CoOp prompts · Base-to-newharmonic mean: 74.73 -> 76.31Improved
increase quantization bits from 1 to 4 (ablation)QCoOp · Base-to-newharmonic mean: 75.92 -> 75.76No clear effect
add prompts in more transformer layers (depth 1 to 6) (ablation)QCoOp · Base-to-newharmonic mean: 75.92 -> 76.90Mixed
quantize visual prompts instead of text prompts (ablation)QCoOp · Base-to-newharmonic mean: 75.92 -> 70.98Hurt
apply QCoOp to SLIP backbone instead of CoOpSLIP · Base-to-new (SLIP)harmonic mean: 55.51 -> 71.07Improved
QCoOp vs CoOp on domain generalizationQCoOp · Domain generalizationtarget average accuracy: 59.28 -> 60.20Improved

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