HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Semantic Segmentation On Camvid

Metrics

Mean IoU

Results

Performance results of various models on this benchmark

Paper Title
SERNet-Former84.62SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks
SIW83.7Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings
DSNet-Base83.32DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation
RTFormer-Base82.5RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
PIDNet-Wider82.0%PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
DeepLabV3Plus + SDCNetAug81.7%Improving Semantic Segmentation via Video Propagation and Label Relaxation
DDRNet2380.6%Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
ETC-Mobile76.3Efficient Semantic Video Segmentation with Per-frame Inference
VideoGCRF75.2Deep Spatio-Temporal Random Fields for Efficient Video Segmentation
DenseDecoder70.9Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
BiSeNet68.7%BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
FC-DenseNet10366.9%The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
EDANet66.4Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
Dilated Convolutions65.3%Multi-Scale Context Aggregation by Dilated Convolutions
DFANet A64.7%DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
Template-Based NAS-arch0 (480x360 inputs)63.9%Template-Based Automatic Search of Compact Semantic Segmentation Architectures
LMDNet63.5Efficient Road Lane Marking Detection with Deep Learning
Template-Based NAS-arch1 (480x360 inputs)63.2%Template-Based Automatic Search of Compact Semantic Segmentation Architectures
DeepLab-MSc-CRF-LargeFOV61.6%Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
ReSeg58.8%ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation
0 of 21 row(s) selected.