AI Paper Atlas

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

Cascade Prompt Learning for Visual-Language Model Adaptation

Ge Wu, Xin Zhang, Zheng Li, Zhaowei Chen, Jiajun Liang, Jian Yang, Xiang Li

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP

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 CasPL boosting prompt to PromptSRCPromptSRC · Base-to-novel, average over 11 datasetsHM: 79.97 -> 82.69Improved
add CasPL boosting prompt to CoOpCoOp · Base-to-novel, average over 11 datasetsHM: 71.66 -> 79.30Improved
add CasPL boosting prompt to CoOpCoOp · Base-to-novel, ImageNetHM: 71.92 -> 72.29Improved
add CasPL to MaPLeMaPLe · Domain generalization, ImageNet-Saccuracy: 49.15 -> 48.81Hurt
add CasPL to PromptSRCPromptSRC · Domain generalization, target averageaccuracy: 63.90 -> 64.44Improved
use in-domain instead of out-domain unlabeled data for the boosting prompt (ablation)PromptSRC + CasPL · 10 datasets few-shotaccuracy: 84.56 -> 85.52Improved
split 16 prompt tokens into 8 frozen boosting plus 8 adapting (ablation)PromptSRC · Base-to-novel, equal total VLP tokensHM: 80.34 -> 83.51Improved
increase prompt depth in both phases from 1 to 12 (ablation)CasPL · Base-to-novel, 10 datasetsHM: 79.95 -> 83.51Improved
keep boosting prompts frozen in the second phase (ablation)CasPL · Base-to-novelHMImproved
add both boosting and adapting prompts versus adapting alone (ablation)CLIP · Base-to-novel, average over 11 datasetsHM: 79.97 -> 82.69Improved
train boosting prompt with ViT-L/14 teacher on small student (ablation)PromptSRC (ViT-B/16) · Base-to-novel, average over 11 datasetsHM: 82.69 vs PromptSRC ViT-L/14 83.17Mixed
increase unlabeled images per class for boosting prompt on DTD (ablation)CasPL · DTD base-to-novelHM: 62.68 -> 76.44Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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