Exploring Channel-Aware Typical Features for Out-of-Distribution Detection（LAPS)

Usage

1. Dataset Preparation

In-distribution dataset

Please download ImageNet-1k and place the training data and validation data in ./datasets/id_data/ILSVRC-2012/train and ./datasets/id_data/ILSVRC-2012/val, respectively.

Out-of-distribution dataset

We have curated 4 OOD datasets from iNaturalist, SUN, Places, and Textures, 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:

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.

Please put all downloaded OOD datasets into ./datasets/ood_data/.

2. Pre-trained Model Preparation

The model we used in the paper is the pre-trained ResNet-50 provided by Pytorch. The download process will start upon running.

3. OOD Detection Evaluation

To reproduce our results, please run:

python eval.py 

The code is improved based on ReAct: Out-of-distribution Detection With Rectified Activations's source code.