AI Paper Atlas

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

Pointly-Supervised Panoptic Segmentation

Junsong Fan, Zhaoxiang Zhang, Tieniu Tan

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 28 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
add boundary criterion to semantic similarity in traversing cost (ablation)point-supervised panoptic model · VOC valPQ: 46.6 -> 48.5Improved
add manifold criterion to semantic similarity in traversing cost (ablation)point-supervised panoptic model · VOC valPQ: 46.6 -> 49.4Improved
add both boundary and manifold criteria (ablation)point-supervised panoptic model · VOC valPQ: 46.6 -> 49.8Improved
add boundary and manifold criteria, effect on stuff classes (ablation)point-supervised panoptic model · VOC valPQ-stuff: 89.1 -> 89.5No clear effect
raise boundary weight lambda_b from 0.1 to 0.5 or 1.0 (ablation)traversing cost · VOC valPQ: 49.8 -> 48.3Hurt
raise manifold weight lambda_m from 0.1 to 1.0 (ablation)traversing cost · VOC valPQ: 49.8 -> 48.9Hurt
sample points near object centers instead of uniformly (ablation)point-supervised panoptic model · VOC valPQ: 49.8 -> 50.9Improved
sample points near borders instead of uniformly (ablation)point-supervised panoptic model · VOC valPQ: 49.8 -> 44.7Hurt
add color prior loss to the semantic segmentation branch (ablation)point-supervised panoptic model · VOC valmIoU: 62.2 -> 67.5Improved
add color prior loss, effect on panoptic quality (ablation)point-supervised panoptic model · VOC valPQ: 41.3 -> 49.8Improved
use 10 points per target instead of 1point-supervised panoptic model · COCO valPQ: 29.3 -> 33.1Improved
use 10 points per target instead of 1point-supervised panoptic model · VOC valPQ: 49.8 -> 56.6Improved

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