Out-of-distribution detection using the pNML regret. NeurIPS2021

Last update: Dec 02, 2022

Overview

OOD Detection

Load conda environment

conda env create -f environment.yml

or install requirements:

while read requirement; do conda install --yes $requirement || pip install $requirement; done < requirements.txt

# Download OOD data
cd bash_scripts
chmod 777 ./download_data.sh
./download_data.sh

# Download pretrained models
chmod 777 ./download_models.sh
./download_models.sh

Download imagenet30

Follow https://github.com/alinlab/CSI

Imagenet30 training set: https://drive.google.com/file/d/1B5c39Fc3haOPzlehzmpTLz6xLtGyKEy4/view

Imagenet30 testing set: https://drive.google.com/file/d/13xzVuQMEhSnBRZr-YaaO08coLU2dxAUq/view

Put and untar under ./data/Imagenet30

.
├── README.md
├── data
│   ├── Imagenet30
│   │   ├── one_class_test
│   │   ├── one_class_test.tar
│   │   ├── one_class_train
│   │   └── one_class_train.tar

Execute methods

Using the pretrained models, score ood detection

cd bash_scripts
chmod 777 ./execute_methods.sh
./execute_methods.sh

Create paper's tables

cd src
python main main_create_tables.py

Out-of-distribution detection using the pNML regret. NeurIPS2021

Related tags

Overview

OOD Detection

Download imagenet30

Execute methods

Owner

Koby Bibas

Genshin-assets - 👧 Public documentation & static assets for Genshin Impact data.

Provide baselines and evaluation metrics of the task: traffic flow prediction

A PyTorch implementation of SIN: Superpixel Interpolation Network

Implementation of BI-RADS-BERT & The Advantages of Section Tokenization.

Training vision models with full-batch gradient descent and regularization

Code for CVPR2021 paper "Robust Reflection Removal with Reflection-free Flash-only Cues"

Improving Generalization Bounds for VC Classes Using the Hypergeometric Tail Inversion

CausaLM: Causal Model Explanation Through Counterfactual Language Models

A simple and useful implementation of LPIPS.

Merlion: A Machine Learning Framework for Time Series Intelligence

Pytorch implementation of Supporting Clustering with Contrastive Learning, NAACL 2021

A more easy-to-use implementation of KPConv

This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

Official implementation of "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"

Caffe implementation for Hu et al. Segmentation for Natural Language Expressions

BARTScore: Evaluating Generated Text as Text Generation

Large scale PTM - PPI relation extraction

Awesome Graph Classification - A collection of important graph embedding, classification and representation learning papers with implementations.

[CVPR 2022] TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

Contrastive Feature Loss for Image Prediction