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

Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training of neural networks"

OneShot Learning-based hotword detection.

ICCV2021: Code for 'Spatial Uncertainty-Aware Semi-Supervised Crowd Counting'

Code Impementation for "Mold into a Graph: Efficient Bayesian Optimization over Mixed Spaces"

Implementation for the paper: Invertible Denoising Network: A Light Solution for Real Noise Removal (CVPR2021).

Simple reimplemetation experiments about FcaNet

Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.

Python wrappers to the C++ library SymEngine, a fast C++ symbolic manipulation library.

Python Algorithm Interview Book Review

Heat transfer problemas solved using python

Wide Residual Networks (WideResNets) in PyTorch

[SDM 2022] Towards Similarity-Aware Time-Series Classification

Code for the AI lab course 2021/2022 of the University of Verona

A curated list of programmatic weak supervision papers and resources

DeepLab is a state-of-art deep learning system for semantic image segmentation built on top of Caffe.

This program will stylize your photos with fast neural style transfer.

Official Pytorch implementation for video neural representation (NeRV)

NaijaSenti is an open-source sentiment and emotion corpora for four major Nigerian languages

This is a custom made virus code in python, using tkinter module.

Code for MSc Quantitative Finance Dissertation