Fabio Cermelli, Matthieu Cord, Arthur Douillard
See installation instructions.
See Preparing Datasets for Mask2Former.
Per-Pixel baseline:
MODEL.MASK_FORMER.PER_PIXEL True
Mask-based methods:
MODEL.MASK_FORMER.SOFTMASK True MODEL.MASK_FORMER.FOCAL True
CoMFormer:
CONT.DIST.PSEUDO True CONT.DIST.KD_WEIGHT 10.0 CONT.DIST.UKD True CONT.DIST.KD_REW True
MiB:
CONT.DIST.KD_WEIGHT 200.0 CONT.DIST.UKD True CONT.DIST.UCE True
PLOP:
CONT.DIST.PSEUDO True CONT.DIST.PSEUDO_TYPE 1 CONT.DIST.POD_WEIGHT 0.001
ADE Semantic Segmenation:
cfg_file=configs/ade20k/semantic-segmentation/maskformer2_R101_bs16_90k.yaml
CONT.BASE_CLS 100 CONT.INC_CLS 50 CONT.MODE overlap
(see examples in scripts/ade.sh
) CONT.BASE_CLS 100 CONT.INC_CLS 10 CONT.MODE overlap
(see examples in scripts/ade10.sh
)CONT.BASE_CLS 100 CONT.INC_CLS 5 CONT.MODE overlap
(see examples in scripts/ade5.sh
)ADE Panoptic Segmenation:
cfg_file=configs/ade20k/panoptic-segmentation/maskformer2_R50_bs16_90k.yaml
CONT.BASE_CLS 100 CONT.INC_CLS 50 CONT.MODE overlap
(see examples in scripts/adps.sh
) CONT.BASE_CLS 100 CONT.INC_CLS 10 CONT.MODE overlap
(see examples in scripts/adps10.sh
)CONT.BASE_CLS 100 CONT.INC_CLS 5 CONT.MODE overlap
(see examples in scripts/adps5.sh
)If you use CoMFormer in your research, please use the following BibTeX entry.
@article{cermelli2023comformer,
title={CoMFormer: Continual Learning in Semantic and Panoptic Segmentation},
author={Fabio Cermelli and Matthieu Cord and Arthur Douillard},
journal={IEEE/CVF Computer Vision and Pattern Recognition Conference},
year={2023}
}
The code is largely based on Mask2Former.