Mining Latent Classes for Few-shot Segmentation

Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao

The codebase contains baseline of our paper Mining Latent Classes for Few-shot Segmentation, ICCV 2021 Oral.

Some key modifications to the simple yet effective metric learning framework:

• Remove the final residual stage in ResNet for stronger generalization
• Remove the final ReLU for feature matching
• Freeze all the BatchNorms from ImageNet pretrained model

Data preparation

Download

Pretrained model: ResNet-50 | ResNet-101

Dataset: Pascal images and ids | Semantic segmentation annotations

File organization

├── ./pretrained
    ├── resnet50.pth
    └── resnet101.pth
    
├── [Your Pascal Path]
    ├── JPEGImages
    ├── SegmentationClass
    └── ImageSets

Run the code

CUDA_VISIBLE_DEVICES=0,1 python -W ignore main.py \
  --dataset pascal --data-root [Your Pascal Path] \
  --backbone resnet50 --fold 0 --shot 1

You may change the backbone from resnet50 to resnet101, change the fold from 0 to 1/2/3, or change the shot from 1 to 5 for other settings.

Acknowledgement

We thank PANet, PPNet, PFENet and other FSS works for their great contributions.

Citation

@inproceedings{yang2021mining,
  title={Mining Latent Classes for Few-shot Segmentation},
  author={Yang, Lihe and Zhuo, Wei and Qi, Lei and Shi, Yinghuan and Gao, Yang},
  journal={ICCV},
  year={2021}
}