AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Turning a CLIP Model Into a Scene Text Spotter

Wenwen Yu, Yuliang Liu, Xingkui Zhu, Haoyu Cao, Xing Sun, Xiang Bai

TPAMI 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 28 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 ResNet50 with plain CLIP ResNet50 backboneDBNet · IC15 detectionF-measure: 87.3 -> 87.7No clear effect
plain CLIP backbone on CTW1500DBNet · CTW1500 detectionF-measure: 83.4 -> 83.4No clear effect
use FastTCM-CR50 backbone instead of ResNet50DBNet · MSRA-TD500 detectionF-measure: 84.9 -> 88.9Improved
use FastTCM-CR50 instead of TCM-CR50DBNet · MSRA-TD500 detectionF-measure: 88.8 -> 88.9Improved
use FastTCM-CR50 backbone instead of ResNet50ABCNet · Total-Text end-to-endH-mean: 64.2 -> 69.5Improved
use FastTCM-CR50 backbone instead of ResNet50DeepSolo · Total-Text end-to-endH-mean: 79.7 -> 79.9No clear effect
use FastTCM-CR50 instead of ResNet50 with few training dataABCNet · Total-Text few-shot 10% dataH-mean: 43.5 -> 52.3Improved
use FastTCM-CR50 on SynthText to IC15 adaptationDBNet · SynthText to IC15 adaptationF-measure: 64.0 -> 77.2Improved
use FastTCM-CR50 on TT to IC15 spotting adaptationABCNet · TT to IC15H-mean: 32.5 -> 48.2Improved
add predefined language prompt 'Text' (ablation)DBNet FastTCM-CR50 · MSRA-TD500 detectionF-measure: 87.4 -> 88.9Improved
add bimodal similarity matching (ablation)TESTR FastTCM-CR50 · TT to IC15 adaptationH-mean: 48.2 -> 53.1Improved
add language prompt generator (ablation)TESTR FastTCM-CR50 · TT to IC15 adaptationH-mean: 45.5 -> 53.1Improved

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