HCNet

Hierarchical Context-Agnostic Network with Contrastive Feature Diversity for One-Shot Semantic Segmentation

Usage

Requirements

python==3.7, torch==1.6, opencv-python, tensorboardX

Dataset

Prepare related datasets: Pascal-5ⁱ (VOC 2012, SBD) and COCO-20ⁱ (COCO 2014)

Pre-trained models

• Pre-trained backbones and models can be found in Google Driver
• Download backbones and put the pth files under initmodel/ folder

Test and Train

• Specify the path of datasets and pre-trained models in the data/config file

• Use the following command

  sh tool/test.sh|train.sh {data} {model} {split_backbone}
  

  E.g. Test HCNet with ResNet50 on the split 0 of PASCAL-5i:

  sh tool/test.sh pascal hcnet split0_resnet50
  

• We provide trained Models with the ResNet-50 and VGG-16 backbone on Pascal-5i and COCO-20i for performance evalution. You can download them from Google Driver

References

The code is based on semseg and PFENet. Thanks for their great work!