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

[cvpr22] Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation

Autoencoders pretraining using clustering

TensorFlow implementation of original paper : https://github.com/hszhao/PSPNet

Memory-Augmented Model Predictive Control

Ready-to-use code and tutorial notebooks to boost your way into few-shot image classification.

Implementation of Shape Generation and Completion Through Point-Voxel Diffusion

thundernet ncnn

Official repository for "On Improving Adversarial Transferability of Vision Transformers" (2021)

Computer Vision Script to recognize first person motion, developed as final project for the course "Machine Learning and Deep Learning"

Open CV - Convert a picture to look like a cartoon sketch in python

Probabilistic Cross-Modal Embedding (PCME) CVPR 2021

Learning to Prompt for Continual Learning

Time series annotation library.

Source code for our paper "Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations"

Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

This repository is a series of notebooks that show solutions for the projects at Dataquest.io.

Simple helper library to convert a collection of numpy data to tfrecord, and build a tensorflow dataset from the tfrecord.

Ἀνατομή is a PyTorch library to analyze representation of neural networks

Automate issue discovery for your projects against Lightning nightly and releases.

Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch.