AI Paper Atlas

Research map / Detection and segmentation / CNN features

CrackFormer: Transformer Network for Fine-Grained Crack Detection

Huajun Liu, Xiangyu Miao, Christoph Mertz, Chengzhong Xu, Hui Kong

ICCV 2021 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 292 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 3x3 conv with Self-AB in encoder and decoder (ablation)SegNet · CrackLS315ODS: gain on ODS and OIS is 9.8% and 8.9%Improved
add Scal-AB (ablation)SegNet · CrackLS315ODS: 9.7% ODS gain and an 8.9% OIS gainImproved
apply Self-AB (ablation)DeepCrack · CrackLS315ODS: 1.1% and 0.3%Improved
apply Scal-AB (ablation)DeepCrack · CrackLS315ODS: 0.9% and 0.5%Improved
combine Self-AB and Scal-AB (ablation)CrackFormer · CrackLS315ODS: 0.7% -0.9%Improved
fuse all stages instead of finest stage S5 (ablation)CrackFormer · CrackTree260ODS: 0.799 -> 0.881Improved
incremental multi-scale fusion S1+S2+S3+S4 vs single scale S1 (ablation)CrackFormer · CrackTree260ODS: 0.680 -> 0.854Improved
fuse all scales vs finest scale S5 (average over datasets) (ablation)CrackFormer · three crack datasetsODS: 8.7% in averageImproved
use deeper stage output S5 vs S1 (ablation)CrackFormer · Stone331ODS: 0.760 -> 0.809Improved
CrackFormer vs DeepCrack architectureCrackFormer · CrackTree260ODS: 0.852 -> 0.881Improved
CrackFormer vs DeepCrack architectureCrackFormer · CrackLS315ODS: 0.853 -> 0.871Improved
CrackFormer vs DeepCrack architectureCrackFormer · Stone331ODS: 0.856 -> 0.877Improved

Later papers that compared with this method

1 later accepted paper reports Crackformer 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