Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/deeplearning-wisc/knn-ood
Code for ICML 2022 paper "Out-of-distribution Detection with Deep Nearest Neighbors"
https://github.com/deeplearning-wisc/knn-ood
Last synced: about 2 months ago
JSON representation
Code for ICML 2022 paper "Out-of-distribution Detection with Deep Nearest Neighbors"
- Host: GitHub
- URL: https://github.com/deeplearning-wisc/knn-ood
- Owner: deeplearning-wisc
- Created: 2022-02-02T20:03:56.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2024-07-12T04:54:01.000Z (3 months ago)
- Last Synced: 2024-07-12T05:55:49.379Z (3 months ago)
- Language: Python
- Homepage:
- Size: 63.5 KB
- Stars: 165
- Watchers: 2
- Forks: 18
- Open Issues: 1
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
# Out-of-distribution Detection with Deep Nearest Neighbors
This is the source code for ICML 2022 paper [Out-of-distribution Detection with Deep Nearest Neighbors](https://arxiv.org/abs/2204.06507)
by Yiyou Sun, Yifei Ming, Xiaojin Zhu and Yixuan Li.
## Usage
### 1. Dataset Preparation for Large-scale Experiment
#### In-distribution dataset
Please download [ImageNet-1k](http://www.image-net.org/challenges/LSVRC/2012/index) and place the training data and validation data in
`./datasets/imagenet/train` and `./datasets/imagenet/val`, respectively.
#### Out-of-distribution dataset
We have curated 4 OOD datasets from
[iNaturalist](https://arxiv.org/pdf/1707.06642.pdf),
[SUN](https://vision.princeton.edu/projects/2010/SUN/paper.pdf),
[Places](http://places2.csail.mit.edu/PAMI_places.pdf),
and [Textures](https://arxiv.org/pdf/1311.3618.pdf),
and de-duplicated concepts overlapped with ImageNet-1k.
For iNaturalist, SUN, and Places, we have sampled 10,000 images from the selected concepts for each dataset,
which can be download via the following links:
```bash
wget http://pages.cs.wisc.edu/~huangrui/imagenet_ood_dataset/iNaturalist.tar.gz
wget http://pages.cs.wisc.edu/~huangrui/imagenet_ood_dataset/SUN.tar.gz
wget http://pages.cs.wisc.edu/~huangrui/imagenet_ood_dataset/Places.tar.gz
```
For Textures, we use the entire dataset, which can be downloaded from their
[original website](https://www.robots.ox.ac.uk/~vgg/data/dtd/).
Please put all downloaded OOD datasets into `./datasets/ood_data`.
### 2. Dataset Preparation for CIFAR Experiment
#### In-distribution dataset
The downloading process will start immediately upon running.
#### Out-of-distribution dataset
We provide links and instructions to download each dataset:
* [SVHN](http://ufldl.stanford.edu/housenumbers/test_32x32.mat): download it and place it in the folder of `datasets/ood_data/svhn`. Then run `python select_svhn_data.py` to generate test subset.
* [Textures](https://www.robots.ox.ac.uk/~vgg/data/dtd/download/dtd-r1.0.1.tar.gz): download it and place it in the folder of `datasets/ood_data/dtd`.
* [Places365](http://data.csail.mit.edu/places/places365/test_256.tar): download it and place it in the folder of `datasets/ood_data/places365/test_subset`. We randomly sample 10,000 images from the original test dataset.
* [LSUN](https://www.dropbox.com/s/fhtsw1m3qxlwj6h/LSUN.tar.gz): download it and place it in the folder of `datasets/ood_data/LSUN`.
* [iSUN](https://www.dropbox.com/s/ssz7qxfqae0cca5/iSUN.tar.gz): download it and place it in the folder of `datasets/ood_data/iSUN`.
* [LSUN_fix](https://drive.google.com/file/d/1KVWj9xpHfVwGcErH5huVujk9snhEGOxE/view?usp=sharing): download it and place it in the folder of `datasets/ood_data/LSUN_fix`.
* [ImageNet_fix](https://drive.google.com/file/d/1sO_-noq10mmziB1ECDyNhD5T4u5otyKA/view?usp=sharing): download it and place it in the folder of `datasets/ood_data/ImageNet_fix`.
* [ImageNet_resize](https://www.dropbox.com/s/kp3my3412u5k9rl/Imagenet_resize.tar.gz): download it and place it in the folder of `datasets/ood_data/Imagenet_resize`.
[//]: # (For example, run the following commands in the **root** directory to download **LSUN**:)
[//]: # (```)
[//]: # (cd datasets/ood_datasets)
[//]: # (wget https://www.dropbox.com/s/fhtsw1m3qxlwj6h/LSUN.tar.gz)
[//]: # (tar -xvzf LSUN.tar.gz)
[//]: # (```)
### 3. Pre-trained model
Please download [Pre-trained models](https://drive.google.com/file/d/13qZeK05YgVWRAHHdl_s20Yb8gKZgP0dG/view?usp=drive_link) and place in the `./checkpoints` folder.
## Preliminaries
It is tested under Ubuntu Linux 20.04 and Python 3.8 environment, and requries some packages to be installed:
* [PyTorch](https://pytorch.org/)
* [scipy](https://github.com/scipy/scipy)
* [numpy](http://www.numpy.org/)
* [sklearn](https://scikit-learn.org/stable/)
* [faiss](https://github.com/facebookresearch/faiss)
* [pytorch-vit](https://github.com/lukemelas/PyTorch-Pretrained-ViT)
* [ylib](https://github.com/sunyiyou/ylib) (Manually download and copy to the current folder)
## Demo
### 1. Demo code for ImageNet Experiment
Run `./demo_imagenet.sh`.
### 2. Demo code for CIFAR Experiment
Run `./demo_cifar.sh`.
## Citation
If you use our codebase, please cite our work:
```
@article{sun2022knnood,
title={Out-of-distribution Detection with Deep Nearest Neighbors},
author={Sun, Yiyou and Ming, Yifei and Zhu, Xiaojin and Li, Yixuan},
journal={ICML},
year={2022}
}
```