AI Paper Atlas

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

What’s the Point: Semantic Segmentation with Point Supervision

Amy Bearman, Olga Russakovsky, Vittorio Ferrari, Li Fei-Fei

ECCV 2016 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 1,003 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 objectness prior to image-level model (ablation)Img (image-level) model · PASCAL VOC 2012 valmIOU: 29.8 -> 32.2Improved
add one point per class supervision to image-level loss (ablation)Img model · PASCAL VOC 2012 valmIOU: 29.8 -> 35.1Improved
add objectness prior to point-supervised model (ablation)1Point Img model · PASCAL VOC 2012 valmIOU: 35.1 -> 42.7Improved
add one point per class to Img + Obj model (ablation)Img + Obj model · PASCAL VOC 2012 valmIOU: 32.2 -> 42.7Improved
annotate all instances (AllPoints) instead of one point per class (ablation)1Point Img + Obj · PASCAL VOC 2012 valmIOU: 42.7 -> 42.7No clear effect
weight all-instance points by rank (1/2^r) (ablation)AllPoints Img + Obj · PASCAL VOC 2012 valmIOU: 42.7 -> 43.4Improved
enlarge supervised area around each point to radius 2, 5, 25 pixels (ablation)1Point Img + Obj · PASCAL VOC 2012 valmIOU: 43.0-43.1No clear effect
collect points from 3 annotators (ablation)1Point Img + Obj · PASCAL VOC 2012 valmIOU: 42.7 -> 43.8Improved
use a different random annotator per image (ablation)1Point Img + Obj · PASCAL VOC 2012 valmIOU: 42.8, 43.4, 43.8 vs 42.7No clear effect
replace human-clicked points with random points sampled on the object from ground truth (ablation)1Point Img + Obj · PASCAL VOC 2012 valmIOU: 42.7 -> 46.1Improved
add 100 fully supervised images to point supervision (hybrid)1Point Img + Obj · PASCAL VOC 2012 valmIOU: 42.7 -> 53.1Improved
replace points with one squiggle per classImg + Obj · PASCAL VOC 2012 valmIOU: 42.7 -> 49.1Improved

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