AI Paper Atlas

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

Open Vocabulary Scene Parsing

Hang Zhao, Xavier Puig, Bolei Zhou, Sanja Fidler, Antonio Torralba

ICCV 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 112 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 hypernym scoring in place of L2 scoring (joint training) (ablation)Joint model · ADE20K zero-shot (500 infrequent classes)hierarchical F-score: 0.5655 -> 0.6174Improved
add hypernym scoring in place of L2 scoring (image stream only) (ablation)Image-stream model · ADE20K zero-shot (500 infrequent classes)hierarchical F-score: 0.5375 -> 0.5937Improved
train concept stream jointly with image stream instead of fixed concept embeddings (hypernym score) (ablation)Hyper model · ADE20K zero-shot (500 infrequent classes)hierarchical F-score: 0.5937 -> 0.6174Improved
train concept stream jointly with image stream (L2 score) (ablation)L2 model · ADE20K zero-shot (500 infrequent classes)hierarchical F-score: 0.5375 -> 0.5655Improved
joint hypernym model instead of Softmax baselineJoint-Hyper · ADE20K zero-shot (500 infrequent classes)information content ratio: 0.1632 -> 0.2226Improved
joint training instead of image-only training (cosine score) (ablation)Cosine model · ADE20K SceneParse150 (150 training classes)mean IoU: 0.2803 -> 0.3152Improved
joint training instead of image-only training (L2 score) (ablation)L2 model · ADE20K SceneParse150 (150 training classes)mean IoU: 0.2174 -> 0.2692Improved
use cosine instead of L2 scoring in joint model (ablation)Joint model · ADE20K SceneParse150 (150 training classes)mean IoU: 0.2692 -> 0.3152Improved
softmax loss and domain-finetuned word vectors in Word2Vec+ vs Word2Vec (ablation)Word2Vec regression · ADE20K SceneParse150 (150 training classes)mean IoU: 0.2918 -> 0.3160Improved
open-vocabulary joint model vs Softmax on closed 150-class parsingJoint-Cosine · ADE20K SceneParse150 (150 training classes)pixel accuracy: 73.55% -> 73.15%Hurt
use Word2Vec+ vs Word2Vec on zero-shot (ablation)Word2Vec regression · ADE20K zero-shot (500 infrequent classes)hierarchical F-score: 0.5507 -> 0.5671Improved
increase number of training classes beyond 500 (ablation)Joint-Hyper · ADE20K zero-shot (500 infrequent classes)hierarchical F-scoreNo clear effect

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