Scene Parsing
54 papers with code • 1 benchmarks • 3 datasets
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
Cityscapes
Stanford Background
UNDD
Subtasks
Greatest papers with code
Pyramid Scene Parsing Network
tensorflow/models
•
•
CVPR 2017
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
Ranked #3 on
Video Semantic Segmentation
on Cityscapes val
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
tensorflow/models
•
•
NeurIPS 2018
Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks.
Ranked #3 on
Human Part Segmentation
on PASCAL-Part
Semantic Understanding of Scenes through the ADE20K Dataset
CSAILVision/semantic-segmentation-pytorch
•
•
Scene parsing, or recognizing and segmenting objects and stuff in an image, is one of the key problems in computer vision.
GINet: Graph Interaction Network for Scene Parsing
PaddlePaddle/PaddleSeg
•
•
ECCV 2020
GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph.
Semantic Flow for Fast and Accurate Scene Parsing
PaddlePaddle/PaddleSeg
•
•
ECCV 2020
A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation.
Ranked #1 on
Real-Time Semantic Segmentation
on Cityscapes test
OCNet: Object Context Network for Scene Parsing
To capture richer context information, we further combine our interlaced sparse self-attention scheme with the conventional multi-scale context schemes including pyramid pooling~\citep{zhao2017pyramid} and atrous spatial pyramid pooling~\citep{chen2018deeplab}.
Ranked #28 on
Semantic Segmentation
on Cityscapes test
PSANet: Point-wise Spatial Attention Network for Scene Parsing
open-mmlab/mmsegmentation
•
•
ECCV 2018
We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes.
Ranked #33 on
Semantic Segmentation
on Cityscapes test
SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications
Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications.
Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs
MIT-SPARK/Kimera
•
•
This mental model captures geometric and semantic aspects of the scene, describes the environment at multiple levels of abstractions (e. g., objects, rooms, buildings), includes static and dynamic entities and their relations (e. g., a person is in a room at a given time).
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
hkchengrex/CascadePSP
•
•
CVPR 2020
In this paper, we propose a novel approach to address the high-resolution segmentation problem without using any high-resolution training data.
Ranked #1 on
Semantic Segmentation
on BIG
(using extra training data)