AI Paper Atlas

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

Background-Insensitive Scene Text Recognition with Text Semantic Segmentation

Liang Zhao, Zhenyao Wu, Xinyi Wu, Greg Wilsbacher, Song Wang

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 15 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
use pretrained SSN instead of jointed training (no SE) (ablation)BINet · STR benchmarks original Totalaccuracy (%): 91.9 -> 92.3Improved
use pretrained SSN instead of jointed training (with SE) (ablation)BINet · STR benchmarks original Totalaccuracy (%): 91.3 -> 92.6Improved
add SE to jointed SSN (ablation)BINet · STR benchmarks original Totalaccuracy (%): 91.9 -> 91.3Hurt
add SE to jointed SSN (ablation)BINet · STR benchmarks developed Total*accuracy (%): 93.2 -> 93.4Improved
add SE to pretrained SSN (ablation)BINet · STR benchmarks original Totalaccuracy (%): 92.3 -> 92.6Improved
add SR on top of pretrained SSN + SE (ablation)BINet · STR benchmarks original Totalaccuracy (%): 92.6 -> 93.1Improved
add SR on top of pretrained SSN + SE (ablation)BINet · STR benchmarks developed Total*accuracy (%): 93.8 -> 94.4Improved
use SE instead of Concat embedding (ablation)BINet · STR benchmarks original Totalaccuracy (%): 85.5 -> 92.6Improved
use SE instead of Add embedding (ablation)BINet · STR benchmarks original Totalaccuracy (%): 92.3 -> 92.6Improved
use SE instead of Multiply embedding (ablation)BINet · STR benchmarks developed Total*accuracy (%): 93.7 -> 93.8Improved
train on real data with synthetic initialization (SI+Real') instead of original ABINet MJ+ST trainingABINet · STR benchmarks developed Total*accuracy (%): 92.6 -> 93.7Improved
replace ABINet with BINet under SI+Real' trainingABINet · STR benchmarks developed Total*accuracy (%): 93.7 -> 94.4Improved

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