AI Paper Atlas

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

Learning to Detect Semantic Boundaries with Image-Level Class Labels

Namyup Kim, Sehyun Hwang, Suha Kwak

IJCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 2 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 WSBDN architecture instead of Class-aware IRNetpseudo label generation · SBD train soft boundaryMF (%): 59.7 -> 62.4Improved
use WSBDN architecture instead of WS-CASENetpseudo label generation · SBD train hard boundaryMF (%): 56.0 -> 59.8Improved
multiply class-agnostic branch with class-aware branch (ablation)WSBDN · SBD train class-awaremAP (%): 46.6 -> 58.0Improved
multiply class-aware branch into class-agnostic branch (ablation)WSBDN · SBD train class-agnosticMF (%): 58.1 -> 68.2Improved
add multi-scale and flip inference (ablation)WSBDN · SBD train hard boundaryMF (%): 56.5 -> 57.7Improved
add NMS without multi-scale/flip (ablation)WSBDN · SBD train hard boundaryMF (%): 56.5 -> 55.5Hurt
add NMS on top of multi-scale/flip (ablation)WSBDN · SBD train hard boundaryMF (%): 57.7 -> 59.8Improved
degrade CAM quality (IoU drops by 10%) (ablation)WSBDN · SBD train pseudo labelsMF: drops by 4.5%Hurt
use ground-truth segmentation masks instead of CAM (ablation)WSBDN · SBD train pseudo labelsMF (%): up to 74.4%Improved
vary line-segment gamma at 10 or above (ablation)WSBDN · SBD train pseudo labelsMF: varying less than 3%No clear effect
replace CASENet with DFF trained on pseudo labelsOurs · SBD testmean MF (%): 59.7 -> 60.7Improved
use ResNet50 instead of VGG16 backboneOurs+CASENet · SBD testmean MF (%): 50.2 -> 59.8Improved

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