AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Learning Camouflaged Object Detection from Noisy Pseudo Label

Jin Zhang, Ruiheng Zhang, Yanjiao Shi, Zhe Cao, Nian Liu, Fahad Shahbaz Khan

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 19 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
Use box annotations as prompts for pseudo-label generation instead of scribbles (ablation)ANet · pseudo-label quality on remaining 80% of trainF-measure: 0.802 -> 0.860Improved
Add box prompts versus no prompts (ablation)ANet · pseudo-label quality on remaining 80% of trainF-measure: 0.751 -> 0.860Improved
Add point prompts versus no prompts (ablation)ANet · pseudo-label quality on remaining 80% of trainF-measure: 0.751 -> 0.755No clear effect
Add box-labeled pseudo-labeled data to 20% full labels instead of unlabeled data (ablation)PNet · COD10KF-measure: 0.771 -> 0.792Improved
Use WSSCOD (20% full + 80% box) versus 20% full only (ablation)PNet · COD10KF-measure: 0.764 -> 0.792Improved
Switch q from 2 to 1 during training (noise correction) instead of fixed q=2 (ablation)L_NC loss · COD10KF-measure: 0.778 -> 0.792Improved
Switch q from 1 to 2 early then 1 versus MAE-form only (ablation)L_NC loss · COD10KF-measure: 0.780 -> 0.792Improved
Use L_NC instead of GCE noise-robust loss (ablation)PNet · COD10KF-measure: 0.759 -> 0.792Improved
Replace the loss with L_NC in SCODSCOD · COD10KF-measure: 0.628 -> 0.665Improved
Replace the loss with L_NC in SINetv2SINetv2 · COD10KF-measure: 0.719 -> 0.734Improved
Replace the loss with L_NC in SINetv2SINetv2 · COD10KS-measure: 0.814 -> 0.814No clear effect
Add 6665 box-only images to trainingPNet_F20 · COD10KS-measure: 0.860 -> 0.901Improved

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