Fully Convolutional Networks for Semantic Segmentation

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation... (read more)

PDF Abstract CVPR 2015 PDF CVPR 2015 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Semantic Segmentation ADE20K FCN Validation mIoU 29.39 # 22
Semantic Segmentation COCO-Stuff test FCN (VGG-16) mIoU 22.7% # 14
Semantic Segmentation PASCAL VOC 2012 test FCN (VGG-16) Mean IoU 62.2% # 53
Semantic Segmentation SkyScapes-Dense FCN8s (ResNet-50) Mean IoU 33.06 # 3
Semantic Segmentation SkyScapes-Lane FCN8s (ResNet-50) Mean IoU 13.74 # 2

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Optic Disc Segmentation Drishti-GS FCN DiceOC 0.8795 # 7
DiceOD 0.9569 # 7
mIoU 0.8392 # 6
Optic Disc Segmentation REFUGE FCN DiceOC 0.8467 # 6
DiceOD 92.56 # 6
mIoU 0.8247 # 5
Multi-tissue Nucleus Segmentation Kumar FCN8 (e) Dice 0.797 # 12
Hausdorff Distance (mm) 31.2 # 17
Semantic Segmentation PASCAL Context FCN-8s mIoU 37.8 # 42

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Dropout
Regularization
Global Average Pooling
Pooling Operations
Dense Connections
Feedforward Networks
ReLU
Activation Functions
Max Pooling
Pooling Operations
Softmax
Output Functions
Convolution
Convolutions
VGG
Convolutional Neural Networks
ResNet
Convolutional Neural Networks