atlas

Research map / Detection and segmentation / CNN features

Geometry-Aware Scene Text Detection With Instance Transformation Network

CVPR 2018 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 102 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 regular convolutional representations with instance-specific geometry-aware transformationsITN with ResNet-50 · MSRA-TD500F-measure: 74.8 -> 80.3Helped
Replace regular convolutional representations with instance-specific geometry-aware transformationsITN with VGG-16 · MSRA-TD500F-measure: 57.0 -> 72.2Helped
Replace regular convolutional representations with instance-specific geometry-aware transformationsITN with ResNet-50 · ICDAR2015 Incidental TextF-measure: 73.4 -> 76.1Helped
Replace regular convolutional representations with instance-specific geometry-aware transformationsITN with VGG-16 · ICDAR2015 Incidental TextF-measure: 75.8 -> 79.5Helped
Add rigid affine transformation constraints rather than using general transformations (ablation)ITN with ResNet-50 · MSRA-TD500F-measure: 78.2% -> 80.3%Helped
Add transformation regression supervision (ablation)ITN with ResNet-50 · MSRA-TD500F-measure: 79.0% -> 80.3%Helped

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