Real-Time Semantic Segmentation
Real-time semantic segmentation is the task of achieving computationally efficient semantic segmentation (while maintaining a base level of accuracy).
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
Greatest papers with code
Pyramid Scene Parsing Network
CVPR 2017
• tensorflow/models
• 
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
This is due to the very invariance properties that make DCNNs good for high level tasks.
SOTA for Scene Segmentation on SUN-RGBD
Fully Convolutional Networks for Semantic Segmentation
Convolutional networks are powerful visual models that yield hierarchies of features.
#3 best model for
Scene Segmentation
on SUN-RGBD
Conditional Random Fields as Recurrent Neural Networks
ICCV 2015
• torrvision/crfasrnn
•
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding.
#10 best model for
Real-Time Semantic Segmentation
on Cityscapes
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.
#2 best model for
Scene Segmentation
on SUN-RGBD
REAL-TIME SEMANTIC SEGMENTATION SCENE SEGMENTATION SCENE UNDERSTANDING
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
Semantic segmentation requires both rich spatial information and sizeable receptive field.
#2 best model for
Real-Time Semantic Segmentation
on CamVid
Multi-Scale Context Aggregation by Dilated Convolutions
• fyu/dilation
• 
State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification.
#4 best model for
Real-Time Semantic Segmentation
on CamVid
The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks
CVPR 2018
• bermanmaxim/LovaszSoftmax
•
The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale invariance - which lends appropriate relevance to small objects, and appropriate counting of false negatives, in comparison to per-pixel losses.
#9 best model for
Real-Time Semantic Segmentation
on Cityscapes
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
Compared to YOLOv2 on the MS-COCO object detection, ESPNetv2 delivers 4. 4% higher accuracy with 6x fewer FLOPs.
#18 best model for
Semantic Segmentation
on PASCAL VOC 2012
IMAGE CLASSIFICATION LANGUAGE MODELLING OBJECT CLASSIFICATION REAL-TIME OBJECT DETECTION REAL-TIME SEMANTIC SEGMENTATION
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
We focus on the challenging task of real-time semantic segmentation in this paper.
#3 best model for
Real-Time Semantic Segmentation
on CamVid