Self-Support Few-Shot Semantic Segmentation

Qi Fan, Wenjie Pei, Yu-Wing Tai, Chi-Keung Tang

The codebase contains the official code of our paper Self-Support Few-Shot Semantic Segmentation, ECCV 2022.

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
    │   ├── 2007_000032.jpg
    │   └── ...
    │
    ├── SegmentationClass
    │   ├── 2007_000032.png
    │   └── ...
    │
    └── ImageSets
        ├── train.txt
        └── val.txt

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.

Performance and Trained Models

Pascal Voc

Setting	Backbone	Refinement	Fold 0	Fold 1	Fold 2	Fold 3	Mean
1-shot	ResNet-50	Yes	61.4	67.8	66.5	50.9	61.7
1-shot	ResNet-101	Yes	63.2	70.4	68.5	56.3	64.6
5-shot	ResNet-50	Yes	67.5	72.3	75.2	62.1	69.3
5-shot	ResNet-101	Yes	70.9	77.1	78.9	66.1	73.3

Acknowledgement

This codebase is built based on MLC's baseline code. We thank MLC and other FSS works for their great contributions.

Citation

@inproceedings{fan2022ssp,
  title={Self-Support Few-Shot Semantic Segmentation},
  author={Fan, Qi and Pei, Wenjie and Tai, Yu-Wing and Tang, Chi-Keung},
  journal={ECCV},
  year={2022}
}