Real-Time Semantic Segmentation
97 papers with code • 8 benchmarks • 12 datasets
Semantic Segmentation is a computer vision task that involves assigning a semantic label to each pixel in an image. In Real-Time Semantic Segmentation, the goal is to perform this labeling quickly and accurately in real-time, allowing for the segmentation results to be used for tasks such as object recognition, scene understanding, and autonomous navigation.
( Image credit: TorchSeg )
Benchmarks
These leaderboards are used to track progress in Real-Time Semantic Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Real-Time Semantic Segmentation models and implementationsDatasets
Cityscapes
NYUv2
COCO-Stuff
CamVid
Kvasir-SEG
Kvasir
Kvasir-Instrument
FLAME
KvasirCapsule-SEG
HelixNet
Most implemented papers
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures.
Pyramid Scene Parsing Network
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
The ability to perform pixel-wise semantic segmentation in real-time is of paramount importance in mobile applications.
Fully Convolutional Networks for Semantic Segmentation
Convolutional networks are powerful visual models that yield hierarchies of features.
Fast-SCNN: Fast Semantic Segmentation Network
The encoder-decoder framework is state-of-the-art for offline semantic image segmentation.
HarDNet: A Low Memory Traffic Network
PingoLH/Pytorch-HarDNet
•
•
ICCV 2019
We propose a Harmonic Densely Connected Network to achieve high efficiency in terms of both low MACs and memory traffic.
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
PaddlePaddle/PaddleSeg
•
•
ECCV 2018
Semantic segmentation requires both rich spatial information and sizeable receptive field.
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
We focus on the challenging task of real-time semantic segmentation in this paper.
SOLOv2: Dynamic and Fast Instance Segmentation
WXinlong/SOLO
•
•
NeurIPS 2020
Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.
Lite-HRNet: A Lightweight High-Resolution Network
HRNet/Lite-HRNet
•
•
CVPR 2021
We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks.
