This is the implementation of the paper "Hypercorrelation Squeeze for Few-Shot Segmentation" by Juhong Min, Dahyun Kang, and Minsu Cho. Implemented on Python 3.7 and Pytorch 1.5.1.

For more information, check out project [website] and the paper on [arXiv].

• Python 3.7
• PyTorch 1.5.1
• cuda 10.1
• tensorboard 1.14

Conda environment settings:

conda create -n hsnet python=3.7
conda activate hsnet

conda install pytorch=1.5.1 torchvision cudatoolkit=10.1 -c pytorch
conda install -c conda-forge tensorflow
pip install tensorboardX

Download following datasets:

1. PASCAL-5ⁱ

Download PASCAL VOC2012 devkit (train/val data):

wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar

Download PASCAL VOC2012 SDS extended mask annotations from our [Google Drive].

2. COCO-20ⁱ

Download COCO2014 train/val images and annotations:

wget http://images.cocodataset.org/zips/train2014.zip
wget http://images.cocodataset.org/zips/val2014.zip
wget http://images.cocodataset.org/annotations/annotations_trainval2014.zip

Download COCO2014 train/val annotations from our Google Drive: [train2014.zip], [val2014.zip]. (and locate both train2014/ and val2014/ under annotations/ directory).

3. FSS-1000

Download FSS-1000 images and annotations from our [Google Drive].

Create a directory '../Datasets_HSN' for the above three few-shot segmentation datasets and appropriately place each dataset to have following directory structure:

../                         # parent directory
├── ./                      # current (project) directory
│   ├── common/             # (dir.) helper functions
│   ├── data/               # (dir.) dataloaders and splits for each FSSS dataset
│   ├── model/              # (dir.) implementation of Hypercorrelation Squeeze Network model 
│   ├── README.md           # intstruction for reproduction
│   ├── train.py            # code for training HSNet
│   └── test.py             # code for testing HSNet
└── Datasets_HSN/
    ├── VOC2012/            # PASCAL VOC2012 devkit
    │   ├── Annotations/
    │   ├── ImageSets/
    │   ├── ...
    │   └── SegmentationClassAug/
    ├── COCO2014/           
    │   ├── annotations/
    │   │   ├── train2014/  # (dir.) training masks (from Google Drive) 
    │   │   ├── val2014/    # (dir.) validation masks (from Google Drive)
    │   │   └── ..some json files..
    │   ├── train2014/
    │   └── val2014/
    └── FSS-1000/           # (dir.) contains 1000 object classes
        ├── abacus/   
        ├── ...
        └── zucchini/

1. PASCAL-5ⁱ

python train.py --backbone {vgg16, resnet50, resnet101} 
                --fold {0, 1, 2, 3} 
                --benchmark pascal
                --lr 1e-3
                --bsz 20
                --logpath "your_experiment_name"

• Training takes approx. 2 days until convergence (trained with four 2080 Ti GPUs).

2. COCO-20ⁱ

python train.py --backbone {resnet50, resnet101} 
                --fold {0, 1, 2, 3} 
                --benchmark coco 
                --lr 1e-3
                --bsz 40
                --logpath "your_experiment_name"

• Training takes approx. 1 week until convergence (trained four Titan RTX GPUs).

3. FSS-1000

python train.py --backbone {vgg16, resnet50, resnet101} 
                --benchmark fss 
                --lr 1e-3
                --bsz 20
                --logpath "your_experiment_name"

• Training takes approx. 3 days until convergence (trained with four 2080 Ti GPUs).

Babysitting training:

Use tensorboard to babysit training progress:

• For each experiment, a directory that logs training progress will be automatically generated under logs/ directory.
• From terminal, run 'tensorboard --logdir logs/' to monitor the training progress.
• Choose the best model when the validation (mIoU) curve starts to saturate.

1. PASCAL-5ⁱ

Pretrained models with tensorboard logs are available on our [Google Drive].

python test.py --backbone {vgg16, resnet50, resnet101} 
               --fold {0, 1, 2, 3} 
               --benchmark pascal
               --nshot {1, 5} 
               --load "path_to_trained_model/best_model.pt"

2. COCO-20ⁱ

Pretrained models with tensorboard logs are available on our [Google Drive].

python test.py --backbone {resnet50, resnet101} 
               --fold {0, 1, 2, 3} 
               --benchmark coco 
               --nshot {1, 5} 
               --load "path_to_trained_model/best_model.pt"

3. FSS-1000

Pretrained models with tensorboard logs are available on our [Google Drive].

python test.py --backbone {vgg16, resnet50, resnet101} 
               --benchmark fss 
               --nshot {1, 5} 
               --load "path_to_trained_model/best_model.pt"

4. Evaluation without support feature masking on PASCAL-5ⁱ

• To reproduce the results in Tab.1 of our main paper, COMMENT OUT line 51 in hsnet.py: support_feats = self.mask_feature(support_feats, support_mask.clone())

Pretrained models with tensorboard logs are available on our [Google Drive].

python test.py --backbone resnet101 
               --fold {0, 1, 2, 3} 
               --benchmark pascal
               --nshot {1, 5} 
               --load "path_to_trained_model/best_model.pt"

• To visualize mask predictions, add command line argument --visualize: (prediction results will be saved under vis/ directory)

  python test.py '...other arguments...' --visualize  

If you use this code for your research, please consider citing:

@InProceedings{min2021hypercorrelation,
    title={Hypercorrelation Squeeze for Few-Shot Segmentation},
    author={Juhong Min and Dahyun Kang and Minsu Cho},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    year={2021}
}