AI Paper Atlas

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

Weakly- and Semi-Supervised Panoptic Segmentation

Qizhu Li, Anurag Arnab, Philip H.S. Torr

ECCV 2018 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 173 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
train the semantic subnetwork and instance subnetwork end-to-end (weak boxes, with COCO) (ablation)weakly supervised panoptic model · Pascal VOC valAP^r_vol: 53.3 -> 55.5Improved
train end-to-end (weak boxes, without COCO pretraining) (ablation)weakly supervised panoptic model · Pascal VOC valAP^r_vol: increase by 3.9 from 51.7Improved
add iterative refinement of approximate ground truth (ablation)weakly supervised model · Pascal VOC valAP^r_volNo clear effect
add iterative refinement of approximate ground truth (ablation)weakly supervised model · Cityscapes valIoU and AP^r_volImproved
use COCO pretraining for the semantic subnetwork (ablation)weakly supervised model · Pascal VOC valIoU (weak): 74.3 -> 75.7Improved
switch COCO annotations from weak to full while VOC stays weak (ablation)weakly supervised model · Pascal VOC valAP^r_vol: 55.5 -> 56.1No clear effect
switch VOC annotations from weak to full while COCO stays weak (ablation)weakly supervised model · Pascal VOC valAP^r_vol: 55.5 -> 58.9Improved
switch from weak to full supervisionsemantic segmentation model · Pascal VOC valIoU: 74.3 -> 77.3Improved
rank stuff instances by mean segmentation confidence instead of constant score (ablation)weakly supervised model · Cityscapes val (stuff classes)AP^r_vol: 26.7 -> 33.1Improved
rank thing instances by mean segmentation confidence instead of detection score (ablation)weakly supervised model · Cityscapes val (thing classes)AP^r_vol: 17.0 -> 14.6Hurt
use bounding boxes for thing classes rather than image-level tags for stuff classesweakly supervised model · Cityscapes valIoU: 60.2 -> 68.2Improved

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