AI Paper Atlas

Research map / Detection and segmentation / CNN features

I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-Shaped Scene Text Detection

Bo Du, Jian Ye, Jing Zhang, Juhua Liu, Dacheng Tao

IJCV 2022 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 53 citations (OpenAlex)

Read the paper

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 Intra-CL module (ablation)Mask R-CNN baseline · ArTF-measure: 74.0 -> 75.0Improved
add Intra-CL module (ablation)Mask R-CNN baseline · Total-TextF-measure: 83.3 -> 84.7Improved
add Intra-CL module (ablation)Mask R-CNN baseline · CTW-1500F-measure: 82.8 -> 84.1Improved
add Inter-CL (GCG) on top of Intra-CL (ablation)Intra-CL · ArTF-measure: 75.0 -> 76.6Improved
use transformer (GCT) instead of average pooling (GCG) for Inter-CL context (ablation)Intra-CL + Inter-CL · ArTF-measure: 76.6 -> 76.4No clear effect
combine GCG and GCT in Inter-CL (ablation)Intra-CL + Inter-CL · ArTF-measure: 76.6 -> 76.5No clear effect
add semi-supervised learning with pseudo labels (ablation)I3CL · ArTF-measure: 76.6 -> 77.5Improved
use 3-path instead of 1-path Intra-CL (ablation)Intra-CL · ArTF-measure: 74.4 -> 75.0Improved
reverse kernel order from 753 to 357 (ablation)Intra-CL · ArTF-measure: 75.0 -> 74.3Hurt
concatenation vs element-wise sum for path fusion (ablation)Intra-CL · ArTF-measure: 74.9 -> 75.0No clear effect
use threshold filter pseudo labels from a single model (ablation)I3CL baseline · ArTF-measure: 76.6 -> 75.5Hurt
use ensemble with Overlap-Mask and Soft-Box for pseudo labels (ablation)I3CL · ArTF-measure: 76.6 -> 77.5Improved

Later papers that compared with this method

1 later accepted paper reports I3CL as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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