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

A simple python module to generate anchor (aka default/prior) boxes for object detection tasks.

CTRL-C: Camera calibration TRansformer with Line-Classification

Riemannian Geometry for Molecular Surface Approximation (RGMolSA)

LibMTL: A PyTorch Library for Multi-Task Learning

Combinatorially Hard Games where the levels are procedurally generated

This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations,

This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their coordinates and detected labels.

This dlib-based facial login system

Official PyTorch Implementation of GAN-Supervised Dense Visual Alignment

Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model

A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising (CVPR 2020 Oral & TPAMI 2021)

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI

Codebase for Amodal Segmentation through Out-of-Task andOut-of-Distribution Generalization with a Bayesian Model

Pytorch Implementation for Dilated Continuous Random Field

Efficient Sharpness-aware Minimization for Improved Training of Neural Networks

Betafold - AlphaFold with tunings

We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

Add-on for importing and auto setup of character creator 3 character exports.