AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark

Joakim Bruslund Haurum, Thomas B. Moeslund

CVPR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 7 citations (OpenAlex)

Check 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 Xie's binary normal/defect classifier before TResNet-LTResNet-L on Sewer-ML · Sewer-ML testF2_CIW: 54.75 -> 55.11Improved
Add Xie's binary normal/defect classifier before TResNet-LTResNet-L on Sewer-ML · Sewer-ML testF1_Normal: 79.88 -> 90.94Improved
Add Xie's binary first stage (ablation)Xie's two-stage classifier · Sewer-ML testF2_CIW: 37.83 -> 48.34Improved
Add Xie's binary first stage (ablation)Xie's two-stage classifier · Sewer-ML testF1_Normal: 0.68 -> 90.62Improved
Add Chen's binary first stage (ablation)Chen's two-stage classifier · Sewer-ML testF2_CIW: 41.74 -> 41.74No clear effect
Add Myrans's binary first stage (ablation)Myrans's two-stage classifier · Sewer-ML testF2_CIW: 19.19 -> 4.11Hurt
Add Myrans's binary first stage (ablation)Myrans's two-stage classifier · Sewer-ML testF1_Normal: 0.00 -> 27.48Improved
Train the second stage on the full dataset, including normal pipes (ablation)Xie's two-stage classifier · Sewer-ML testF2_CIW: 48.34 -> 31.82Hurt
Train the second stage on the full dataset, including normal pipes (ablation)Xie's two-stage classifier · Sewer-ML testF1_Normal: 90.62 -> 87.95Hurt
Train the second stage on the full dataset, including normal pipes (ablation)Chen's two-stage classifier · Sewer-ML testF2_CIW: 41.74 -> 43.14Improved
Train the second stage on the full dataset, including normal pipes (ablation)Myrans's two-stage classifier · Sewer-ML testF2_CIW: 4.11 -> 2.61Hurt
Train the second stage on the full dataset, including normal pipes (ablation)Myrans's two-stage classifier · Sewer-ML testF1_Normal: 27.48 -> 27.48No clear effect

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