AI Paper Atlas

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

Weakly-Supervised Camouflaged Object Detection with Scribble Annotations

Ruozhen He, Qihua Dong, Jiaying Lin, Rynson W.H. Lau

AAAI 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 118 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 scribble-supervised CRNet instead of SCWSSODWeakly supervised COD · CAMO, CHAMELEON, and COD10KMAE: CAMO: 0.102 -> 0.092; CHAMELEON: 0.053 -> 0.046; COD10K: 0.055 -> 0.049Improved
Use scribble-supervised CRNet instead of SCWSSODWeakly supervised COD · CAMO, CHAMELEON, and COD10KS-measure: CAMO: 0.713 -> 0.735; CHAMELEON: 0.792 -> 0.818; COD10K: 0.710 -> 0.733Improved
Use scribble-supervised CRNet instead of SCWSSODWeakly supervised COD · CAMO, CHAMELEON, and COD10KE-measure: CAMO: 0.795 -> 0.815; CHAMELEON: 0.881 -> 0.897; COD10K: 0.805 -> 0.832Improved
Use scribble-supervised CRNet instead of SCWSSODWeakly supervised COD · CAMO, CHAMELEON, and COD10Kweighted F-measure: CAMO: 0.618 -> 0.641; CHAMELEON: 0.714 -> 0.744; COD10K: 0.546 -> 0.576Improved
Add AGE to the backbone (ablation)CRNet on CAMO · CAMOMAE: 0.104 -> 0.100Improved
Add LCC to backbone + AGE (ablation)CRNet on CAMO · CAMOMAE: 0.100 -> 0.099Improved
Add LSR to backbone + AGE (ablation)CRNet on CAMO · CAMOMAE: 0.100 -> 0.098Improved
Use both LCC and LSR instead of LCC alone (ablation)CRNet on CAMO · CAMOMAE: 0.099 -> 0.092Improved
Add flipping to resizing in cross-view transforms (ablation)Cross-view consistency loss · CAMOMAE: 0.097 -> 0.094Improved
Add translation to resizing and flipping in cross-view transforms (ablation)Cross-view consistency loss · CAMOMAE: 0.094 -> 0.094No clear effect
Add cropping to resizing, flipping, and translation in cross-view transforms (ablation)Cross-view consistency loss · CAMOMAE: 0.094 -> 0.092Improved
Add the reliability bias to cross-view consistency (ablation)Cross-view consistency loss with feature-guided loss · CAMOS-measure: 0.723 -> 0.726Improved

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