Panoptic Feature Pyramid Networks

The recently introduced panoptic segmentation task has renewed our community's interest in unifying the tasks of instance segmentation (for thing classes) and semantic segmentation (for stuff classes). However, current state-of-the-art methods for this joint task use separate and dissimilar networks for instance and semantic segmentation, without performing any shared computation... (read more)

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Panoptic Segmentation Cityscapes val Panoptic FPN (ResNet-101) PQ 58.1 # 16
PQst 62.5 # 11
PQth 52 # 15
mIoU 75.7 # 12
AP 33 # 14
Panoptic Segmentation COCO panoptic Panoptic-FPN-ResNet-101 PQ 43.0 # 7
Panoptic Segmentation Indian Driving Dataset Panoptic FPN PQ 46.7 # 4
Panoptic Segmentation KITTI Panoptic Segmentation Panoptic FPN PQ 39.3 # 4

Methods used in the Paper


METHOD TYPE
Softmax
Output Functions
Group Normalization
Normalization
Random Scaling
Image Data Augmentation
ResNeXt Block
Skip Connection Blocks
Grouped Convolution
Convolutions
ResNeXt
Convolutional Neural Networks
Panoptic FPN
Feature Extractors
FPN
Feature Extractors
Average Pooling
Pooling Operations
Residual Connection
Skip Connections
ReLU
Activation Functions
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Bottleneck Residual Block
Skip Connection Blocks
Global Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Kaiming Initialization
Initialization
Max Pooling
Pooling Operations
Convolution
Convolutions
ResNet
Convolutional Neural Networks