SOTAVerified

Scene Parsing

Scene parsing is to segment and parse an image into different image regions associated with semantic categories, such as sky, road, person, and bed. MIT Description

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 161–170 of 199 papers

TitleStatusHype
Real-Time Panoptic Segmentation from Dense Detections—0
Recurrent Convolutional Neural Networks for Scene Parsing—0
Recyclable Semi-supervised Method Based on Multi-model Ensemble for Video Scene Parsing—0
Re:PolyWorld - A Graph Neural Network for Polygonal Scene Parsing—0
A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization—0
LF Tracy: A Unified Single-Pipeline Approach for Salient Object Detection in Light Field CamerasCode0
Toward Achieving Robust Low-Level and High-Level Scene ParsingCode0
Scene Parsing via Integrated Classification Model and Variance-Based RegularizationCode0
Scene Parsing with Global Context EmbeddingCode0
Unlocking the Full Potential of Small Data with Diverse SupervisionCode0
Show:102550
← PrevPage 17 of 20Next →
All datasetsPGDP5KCityscapes test

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PGDPNetTotal Accuracy84.7—Unverified
2Inter-GPSTotal Accuracy27.3—Unverified
#ModelMetricClaimedVerifiedStatus
1VCD No CoarsemIoU82.3—Unverified