AI Paper Atlas

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

Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation

Hui Zhang, Henghui Ding

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 83 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 open-set rejection (ablation)prototype matching ZSS · Pascal VOC 2012 (cow/motorbike unseen)hIoU: 5.4 -> 60.5Improved
add open-set rejection (ablation)prototype matching ZSS · Pascal VOC 2012 (cat/tv unseen)hIoU: 6.1 -> 62.2Improved
add open-set rejection (ablation)prototype matching ZSS · Pascal VOC 2012 (cow/motorbike unseen)unseen mIoU: 2.8 -> 51.3Improved
use ground-truth rejection instead of learned open-set rejection (oracle upper bound) (ablation)open-set rejection · Pascal VOC 2012 (cow/motorbike unseen)hIoU: 60.5 -> 69.8Improved
use ground-truth rejection instead of learned open-set rejection (oracle upper bound) (ablation)open-set rejection · Pascal VOC 2012 (cat/tv unseen)hIoU: 62.2 -> 70.1Improved
replace direct word-embedding prototypes with a learned projection network (ablation)prototype matching ZSS · Pascal VOC 2012 (aeroplane/sofa unseen)hIoU: 65.0 -> 70.2Improved
replace direct word-embedding prototypes with a learned projection network (ablation)prototype matching ZSS · Pascal VOC 2012 (bird/boat unseen)hIoU: 62.7 -> 66.9Improved
use trainable prototypes instead of a convolutional classifier (ablation)supervised segmentation network · Pascal VOC 2012 (supervised)mIoU: 76.8 -> 76.9No clear effect
proposed method versus CSRLprototypical matching + OSR · Pascal VOC 2012 (2 unseen classes)hIoU: 56.3 -> 60.5Improved
proposed method versus CSRL as unseen classes grow to 10prototypical matching + OSR · Pascal VOC 2012 (10 unseen classes)hIoU: 31.0 -> 46.1Improved
proposed method versus ZS3+GCprototypical matching + OSR · Pascal Context (2 unseen classes)hIoU: 34.8 -> 46.3Improved
proposed method versus CaGNetprototypical matching + OSR · Pascal Context (10 unseen classes)hIoU: 21.2 -> 27.7Improved

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