AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment

Kaixin Wang, Jun Hao Liew, Yingtian Zou, Daquan Zhou, Jiashi Feng

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 1,645 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 prototype alignment regularization (PAR) (ablation)PANet · PASCAL-5i 1-shotmean-IoU: 47.2 -> 48.1Improved
add prototype alignment regularization (PAR) (ablation)PANet · PASCAL-5i 5-shotmean-IoU: 54.9 -> 55.7Improved
add PAR: distance between query and support prototypes (ablation)PANet · PASCAL-5i split-1 5-shotprototype Euclidean distance (lower is better): 42.6 -> 32.2Improved
train the network on PASCAL-5i instead of ImageNet-init onlyPANet-init to PANet · PASCAL-5i 1-shotmean-IoU: 35.3 -> 48.1Improved
train the network on PASCAL-5i instead of ImageNet-init onlyPANet-init to PANet · PASCAL-5i 5-shotmean-IoU: 46.7 -> 55.7Improved
use scribble instead of dense support annotationPANet · PASCAL-5i 1-shotmean-IoU: 48.1 -> 44.8Hurt
use scribble instead of dense support annotationPANet · PASCAL-5i 5-shotmean-IoU: 55.7 -> 54.6Hurt
use bounding box instead of dense support annotationPANet · PASCAL-5i 1-shotmean-IoU: 48.1 -> 45.1Hurt
use bounding box instead of dense support annotationPANet · PASCAL-5i 5-shotmean-IoU: 55.7 -> 52.8Hurt
use scribbles rather than bounding boxes with more supportPANet · PASCAL-5i 5-shotmean-IoU: 54.6 -> 52.8Improved
increase support set from 1 to 5 shotsPANet · PASCAL-5imean-IoU: 48.1 -> 55.7Improved
increase support set from 1 to 5 shotsco-FCN · PASCAL-5imean-IoU: 41.1 -> 41.4No clear effect

Later papers that compared with this method

41 later accepted papers report PANet as a baseline in their results tables; 33 of them report a better number on most of the results they share with it.

33 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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