You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Following the instructions from the official website. The code is developed and tested with the Pytorch 1.11.0
Install the rest.
pip install -r requirements.txt
Dataset Preparation
ID dataset
Download ImageNet-1k dataset from the official Website. Put the dataset in the folder data/imagenet.
OOD dataset
OpenImage-O: Follow the instruction from ViM. Put the dataset in the folder data/openimaeg_o
ImageNet-O: Follow the official guidance. Put the dataset in data/imagenet_o
iNaturalist, SUN, Places, Textures: Follow the instruction from MOS. Put them in data/inaturalist, data/Places, data/Textures, and data/Textures, respectively.
Pretrained Models
ResNet-50 on ImageNet. No external download required. Will use the released model by Pytorch.
ResNet-Supcon on ImageNet. Download from KNN-OOD, and place in ./pretrained_models/ImageNet
Part of the code is modified from ViM, MOS, and KNN-OOD repo.
Citation
If you find WDiscOOD helpful in your research or application, please consider citing our paper:
@article{chen2023wdiscood,
title={WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminative Analysis},
author={Chen, Yiye and Lin, Yunzhi and Xu, Ruinian and Vela, Patricio A},
journal={International Conference on Computer Vision (ICCV)},
year={2023}
}
About
[ICCV2023] Official Implementation of ICCV 2023 paper, WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant Analysis