HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Semantic Segmentation On Pascal Voc 2012

Metrics

Mean IoU

Results

Performance results of various models on this benchmark

Model Name
Mean IoU
Paper TitleRepository
FCN (VGG-16)62.2%Fully Convolutional Networks for Semantic Segmentation
Dilated FCN-2s VGG1969%Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation
Light-Weight-RefineNet-5081.1%Light-Weight RefineNet for Real-Time Semantic Segmentation
Light-Weight-RefineNet-10182.0%Light-Weight RefineNet for Real-Time Semantic Segmentation
DeepLabv3+ (Xception-JFT)89.0%Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Smooth Network with Channel Attention Block86.2%Learning a Discriminative Feature Network for Semantic Segmentation
SANet (pretraining on COCO dataset)86.1%Squeeze-and-Attention Networks for Semantic Segmentation
ESPNet63.01%ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
TuSimple83.1%Understanding Convolution for Semantic Segmentation
PSPNet85.4%Pyramid Scene Parsing Network
ParseNet69.8%ParseNet: Looking Wider to See Better
G256.7%Exploiting saliency for object segmentation from image level labels-
CentraleSupelec Deep G-CRF80.2%Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
WASPnet-CRF (ours)79.6%Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
EncNet (ResNet-101)82.9%Context Encoding for Semantic Segmentation
SSDD65.5Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation
Dilated Convolutions67.6%Multi-Scale Context Aggregation by Dilated Convolutions
CASIA_IVA_SDN86.6%Stacked Deconvolutional Network for Semantic Segmentation-
ESPNetv268.0%ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
Deeplab-v2 with Lovasz-Softmax loss79.00%The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
0 of 51 row(s) selected.