AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation

Beom Young Kim, Sung Ju Hwang

ECCV 2026 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 0 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
refine with Phoenix instead of SAMRefinerPointWSSIS 1% masks · LVIS PointWSSIS 1%AP mask: 21.8 -> 28.7Improved
refine with PhoenixMask R-CNN R50 · LVISAP mask: 39.8 -> 46.9Improved
refine strong models with PhoenixMaskDINO · LVISAP mask: 56.8 -> 58.0Improved
refine with SAMRefiner on strong modelMaskDINO · LVISAP mask: 56.8 -> 57.0No clear effect
refine Cityscapes masks with SAMRefinerMask R-CNN R50 · CityscapesAP: 36.1 -> 32.5Hurt
refine DIS masks with PhoenixDIS U-Net · DIS averageIoU: 54.7 -> 75.7Improved
add adversarial semantic-aware perturbation instead of morphological noise (ablation)Phoenix · LVIS PointWSSIS 1%AP mask: 23.8 -> 28.7Improved
add contrastive CMRL loss (ablation)Phoenix · LVIS PointWSSIS 1%AP mask: 26.9 -> 28.7Improved
apply adversarial perturbation to SegRefiner (ablation)SegRefiner · DIS average (U-Net)IoU: 58.7 -> 71.8Improved
train Phoenix on masks from real models instead of adversarial noise (ablation)Phoenix · DIS average (U-Net)IoU: 75.7 -> 67.6Hurt
higher IoU threshold tau (ablation)Phoenix · LVIS PointWSSIS 1%AP mask: 28.2 -> 24.2Mixed
change adversarial criterion (Dice vs L1) (ablation)Phoenix · LVIS PointWSSIS 1%AP mask: 27.7 -> 28.7No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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