AI Paper Atlas

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

Point-supervised Panoptic Segmentation via Estimating Pseudo Labels from Learnable Distance

Jing Li, Junsong Fan, Zhaoxiang Zhang

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 1 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
estimate pseudo labels with a learnable distance branch instead of rule-based Dijkstra distancespoint-supervised panoptic segmentation · PASCAL VOC val (P1, Swin-L)PQ: 61.0 -> 68.5Improved
same, with ten-point labels on COCOEPLD R50 · COCO val (P10)PQ: 35.2 -> 41.3Improved
aggregate anchor queries from fusion feature rather than learned position embedding (ablation)EPLD · PASCAL VOC val (P1)PQ: 51.4 -> 56.6Improved
add class embedding (E_cls) and class loss (L_cls) for query enhancing (ablation)EPLD · PASCAL VOC val (P1)PQ: 42.1 -> 56.6Improved
add self-training loss with last-layer pseudo labels (ablation)EPLD · PASCAL VOC val (P1)PQ: 15.6 -> 56.6Improved
add color-prior loss (ablation)EPLD · PASCAL VOC val (P1)PQ: 46.5 -> 56.6Improved
use iterative decoder layers (6) with re-aggregated queries instead of 1 or 2 (ablation)EPLD · PASCAL VOC val (P1)PQ: 3.5 -> 56.6 (1 layer vs 6)Improved
increase decoder layers from 6 to 7 (ablation)EPLD · PASCAL VOC val (P1)PQ: 56.6 -> 55.9Hurt
train panoptic branch with distance-branch pseudo labels instead of point labels (ablation)Panoptic SegFormer head · PASCAL VOC val (P1)PQ: 19.5 -> 56.6Improved
use multi-scale features F1, F2, F3 in fusion and decoder instead of fewer scales (ablation)EPLD · PASCAL VOC val (P1)PQ: 55.6 -> 56.6 (decoder F1 only vs full)Improved
use EPLD pseudo labels instead of SAM (ViT-H) prompted with point labelsPanoptic SegFormer Swin-L · PASCAL VOC valPQ: 60.6 -> 72.2Improved

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