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
Pretrained model: ResNet-50 | ResNet-101
Dataset: Pascal images and ids | Semantic segmentation annotations
├── ./pretrained
├── resnet50.pth
└── resnet101.pth
├── [Your Pascal Path]
├── JPEGImages
├── SegmentationClass
└── ImageSets
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.
We thank PANet, PPNet, PFENet and other FSS works for their great contributions.
@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}
}