AI Paper Atlas

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

Adversarial Erasing Framework via Triplet with Gated Pyramid Pooling Layer for Weakly Supervised Semantic Segmentation

Sung-Hoon Yoon, Hyeokjun Kweon, Jegyeong Cho, Shinjeong Kim, Kuk-Jin Yoon

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 65 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
replace GAP with Gated Pyramid Pooling (coarse-to-fine) (ablation)classifier · VOC 2012 train (CAM pseudo-labels)mIoU: 48.4 -> 54.2Improved
use larger pooling bin size in GPP (ablation)GPP layer · VOC 2012 train (CAM pseudo-labels)mIoU: 49.9 -> 53.1Improved
aggregate pyramid with coarse-to-fine gated conv instead of averaging (ablation)GPP layer · VOC 2012 train (CAM pseudo-labels)mIoU: 53.3 -> 54.2Improved
aggregate with fine-to-coarse gating instead of coarse-to-fine (ablation)GPP layer · VOC 2012 train (CAM pseudo-labels)mIoU: 54.2 -> 51.3Hurt
add triplet adversarial erasing (soft attraction) to GPP (ablation)AEFT · VOC 2012 train (CAM pseudo-labels)mIoU: 54.2 -> 55.0Improved
add repelling loss to attraction loss (ablation)AEFT · VOC 2012 train (CAM pseudo-labels)mIoU: 55.0 -> 56.0Improved
use rigid classification labels for the erased image instead of triplet (ablation)AEFT · VOC 2012 train (CAM pseudo-labels)mIoU: 54.2 -> 53.4Hurt
use GPP feature as embedding instead of CAMs (ablation)AEFT · VOC 2012 train (CAM pseudo-labels)mIoU: 54.6 -> 56.0Improved
maximize distance between eA and eN instead of eAL and eN (ablation)AEFT · VOC 2012 train (CAM pseudo-labels)mIoU: 56.0 -> 54.1Hurt
apply CRF to AEFT CAMsAEFT · VOC 2012 train (CAM pseudo-labels)mIoU: 56.0 -> 63.5Improved
apply random walk after CRFAEFT · VOC 2012 train (CAM pseudo-labels)mIoU: 63.5 -> 71.0Improved

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