AI Paper Atlas

Research map / Detection and segmentation / CNN features

Sequential Deformation for Accurate Scene Text Detection

Shanyu Xiao, Liangrui Peng, Ruijie Yan, Keyu An, Gang Yao, Jaesik Min

ECCV 2020 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 37 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 the Sequential Deformation Module (ablation)Mask R-CNN baseline (ResNet-18) · ICDAR 2017 MLTF-measure (%): 74.84 -> 75.62Improved
add the Sequential Deformation Module (ablation)Mask R-CNN baseline (ResNet-50) · ICDAR 2017 MLTF-measure (%): 77.07 -> 77.62Improved
add auxiliary character counting to SDM (ablation)SDM (ResNet-18) · ICDAR 2017 MLTF-measure (%): 75.62 -> 76.00Improved
add auxiliary character counting to SDM (ablation)SDM (ResNet-50) · ICDAR 2017 MLTF-measure (%): 77.62 -> 78.08Improved
use character recognition instead of counting as auxiliary task (ablation)SDM (ResNet-50) · ICDAR 2017 MLTF-measure (%): 77.62 -> 77.64No clear effect
increase sequential sampling iteration number T up to 5 (ablation)SDM (ResNet-18) · ICDAR 2017 MLTF-measure (%): F-measure firstly increases and then saturates for T >= 5Improved
auxiliary counting with T = 0 (single feature vector) (ablation)SDM (ResNet-18) · ICDAR 2017 MLTF-measure (%): improvement of 0.4%Improved
add SDM and counting to the baselineMask R-CNN (ResNet-50) · Total-TextF-measure (%): 86.16 -> 86.91Improved
add SDM to the baselineMask R-CNN (ResNet-50) · CTW1500F-measure (%): 83.06 -> 84.01Improved
use multi-scale testingOurs (ResNet-50) · ICDAR 2017 MLTF-measure (%): 78.08 -> 80.61Improved
use multi-scale testingOurs (ResNet-50) · ICDAR 2015F-measure (%): 88.57 -> 90.57Improved
use multi-scale testingOurs (ResNet-50) · Total-TextF-measure (%): 86.91 -> 88.37Improved

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