Organizers:
- [2023.03.01] The Segmentation in the Wild Challenge had been launched and ready for submitting results!
- [2023.02.28] We release Segmentation In the Wild dataset and evaluation code.
The branch includes:
- Dataset The download link for SGinW dataset;
- Evaluation On the fly evaluation code supported X-Decoder evaluation.
pip3 install torch==1.13.1 torchvision==0.14.1 --extra-index-url https://download.pytorch.org/whl/cu113
python -m pip install 'git+https://github.com/MaureenZOU/detectron2-xyz.git'
pip install git+https://github.com/cocodataset/panopticapi.git
python -m pip install -r requirements.txt
# sometime this script will report an error when download the zip, please simply copy the command (This is cuased by bad character embedding)
sh install_cococapeval.sh
Please download the dataset HERE!
.
βββ seginw/
βββ Airplane-Parts/
β βββ train/
β β βββ *.jpg
β β βββ _annotations_min1cat.coco.json
β βββ train_10shot/
β β βββ ...
β βββ valid/
β βββ ...
βββ Bottles/
β βββ ...
βββ ...
- Evaluate under Framework X-Decoder
mpirun -n 8 python eval.py evaluate --conf_files configs/xdecoder/svlp_focalt_lang.yaml --overrides WEIGHT /pth/to/ckpt
Note: Due to zero-padding, filling a single gpu with multiple images may decrease the performance.
- Evaluate Using Json File
ADE | ADE-full | SUN | SCAN | SCAN40 | Cityscape | BDD | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
model | ckpt | PQ | AP | mIoU | mIoU | mIoU | PQ | mIoU | mIoU | PQ | mAP | mIoU | PQ | mIoU |
X-Decoder | BestSeg Tiny | 19.1 | 10.1 | 25.1 | 6.2 | 35.7 | 30.3 | 38.4 | 22.4 | 37.7 | 18.5 | 50.2 | 16.9 | 47.6 |
Please refer to detailed format HERE : )
.
βββ ade.json/
β βββ {"ADE150-mIoU": "x", "ADE150-PQ": "x", "ADE150-mAP": "x", "ADE847-mIoU": "x"}
βββ seginw_Airplane-Parts_val.json/
β βββ coco format
βββ seginw_Bottles_val.json
βββ seginw_Brain-Tumor_val.json
βββ seginw_Chicken_val.json
βββ ...
@article{zou2022xdecoder,
author = {Zou, Xueyan and Dou, Zi-Yi and Yang, Jianwei and Gan, Zhe and Li, Linjie and Li, Chunyuan and Dai, Xiyang and Wang, Jianfeng and Yuan, Lu and Peng, Nanyun and Wang, Lijuan and Lee, Yong Jae and Gao, Jianfeng},
title = {Generalized Decoding for Pixel, Image and Language},
publisher = {arXiv},
year = {2022},
}