AI Paper Atlas

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

Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning

Chun-Mei Feng, Kai Yu, Xinxing Xu, Salman Hameed Khan, Rick Siow Mong Goh, Wangmeng Zuo, Yong Liu

TPAMI 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Feature calibration for unseen-class detection · 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
replace text captions with synthetic images from text-to-image model (ablation)TaI-DPT · VOC 2007 (zero-shot)mAP: 88.3 -> 90.8Improved
add text captions to synthetic-image training (ablation)T2I-PAL · VOC 2007 (zero-shot)mAP: 90.8 -> 91.5Improved
add original annotated images to training (ablation)T2I-PAL · VOC 2007 (zero-shot)mAP: 91.5 -> 91.6No clear effect
add shared adapter (ablation)T2I-PAL · MS-COCO (zero-shot)mAP: 70.6 -> 71.4Improved
use local adapter instead of global plus local (ablation)T2I-PAL · MS-COCO (zero-shot)mAP: 70.7 -> 71.4Improved
add adapter to reduce modality gap (ablation)T2I-PAL · MS-COCO cosine similaritycosine similarity: 0.3890 -> 0.6110Improved
use synthetic images instead of captions for modality gap (ablation)T2I-PAL · MS-COCO cosine similaritycosine similarity: 0.3178 -> 0.3890Improved
increase gamma from 0.2 to 1 (all synthetic) (ablation)T2I-PAL · VOC 2007 / MS-COCOmAP: 91.1 -> 90.4Hurt
increase synthetic data to 6x (ablation)T2I-PAL · VOC 2007 (zero-shot)mAP: 90.8 -> 91.5Improved
use 2x additional text data (ablation)T2I-PAL · VOC 2007 (zero-shot)mAP: 91.5 -> 91.8Improved
use LLaMA-generated captions (ablation)T2I-PAL · MS-COCO (zero-shot)mAP: 71.4 -> 71.2No clear effect
use ResNet-101 instead of ResNet-50 (ablation)T2I-PAL · MS-COCO (zero-shot)mAP: 88.80 -> 91.50Improved

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