Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models

Related tags

Deep LearningLMPBT
Overview

LMPBT

Supplementary code for the Paper entitled ``Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models"

  1. Specification of dependencies Pytorch 1.7.1 torchvision 0.8.2 Scikit-learn 0.22 PyHessian (See, https://github.com/amirgholami/PyHessian.) pip install torch==1.7.1 torchvision==0.8.2 pip install pyhessian pip install scikit-learn

  2. Dataset MNIST, FASHION-MNIS, CIFAR-10, CIFAR-100, and SVHN : downloaded from torchvision.datasets CelebA : http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html

  3. Training code We refer to the following code for model training : VAE : https://github.com/XavierXiao/Likelihood-Regret

To train the VAEs, use appropriate arguments and run this command: python train_vae.py

We refer to the following code for computing the low-rank-approximation of Hessian : https://github.com/amirgholami/PyHessian

To compute the top eigenvalues and eigenvectors of VAE models, run this command: python get_eig_vecs_vae.py

  1. Evaluation code To comput the LMPBT-scores using the VAE models, run this command: python get_lmpbt_score.py

  2. We provided the LMPBT socres of a VAE trained on CIFAR-100 and tested on CIFAR-100 as an in-distribution dataset, SVHN and CelebA as an OOD dataset. To comput the OOD performance metrics (AUROC, AUPR and FPR80) of these experiments, run this command: python get_metrics.py

  3. Pre-trained models We provided the pretrained VAE, trained on CIFAR-100.

The model can be loaded using the following code.

parser.add_argument('--state_E', default='./models/cifar100_netE.pth', help='path to encoder checkpoint')

parser.add_argument('--state_G', default='./models/cifar100_netG.pth', help='path to encoder checkpoint')

netG = DVAE.DCGAN_G(opt.imageSize, nz, nc, ngf, ngpu)

state_G = torch.load(opt.state_G, map_location=device)

netG.load_state_dict(state_G)

netE = DVAE.Encoder(opt.imageSize, nz, nc, ngf, ngpu)

state_E = torch.load(opt.state_E, map_location=device)

netE.load_state_dict(state_E)

VQGAN+CLIP Colab Notebook with user-friendly interface.

VQGAN+CLIP and other image generation system VQGAN+CLIP Colab Notebook with user-friendly interface. Latest Notebook: Mse regulized zquantize Notebook

Justin John 227 Jan 05, 2023
[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

FaPN: Feature-aligned Pyramid Network for Dense Image Prediction [arXiv] [Project Page] @inproceedings{ huang2021fapn, title={{FaPN}: Feature-alig

EMI-Group 175 Dec 30, 2022
Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxiang Wang, Han Zhao, Bo Li.

Bridging Multi-Task Learning and Meta-Learning Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Trainin

AI Secure 57 Dec 15, 2022
A Keras implementation of CapsNet in the paper: Sara Sabour, Nicholas Frosst, Geoffrey E Hinton. Dynamic Routing Between Capsules

NOTE This implementation is fork of https://github.com/XifengGuo/CapsNet-Keras , applied to IMDB texts reviews dataset. CapsNet-Keras A Keras implemen

Lauro Moraes 5 Oct 23, 2022
Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis in JAX

SYMPAIS: Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis Overview | Installation | Documentation | Examples | Notebo

Yicheng Luo 4 Sep 13, 2022
A Pytree Module system for Deep Learning in JAX

Treex A Pytree-based Module system for Deep Learning in JAX Intuitive: Modules are simple Python objects that respect Object-Oriented semantics and sh

Cristian Garcia 216 Dec 20, 2022
Java and SHACL code commented in the paper "Towards compliance checking in reified I/O logic via SHACL" submitted to ICAIL 2021

shRIOL The subfolder shRIOL contains Java files to execute the SHACL files on the OWL ontology. To compile the Java files: "javac -cp ./src/;./lib/* -

1 Dec 06, 2022
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

Deep Reinforcement Learning Agents This repository contains a collection of reinforcement learning algorithms written in Tensorflow. The ipython noteb

Arthur Juliani 2.2k Jan 01, 2023
Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder,

Chinese mandarin text to speech based on Fastspeech2 and Unet This is a modification and adpation of fastspeech2 to mandrin(普通话). Many modifications t

291 Jan 02, 2023
This repository provides the code for MedViLL(Medical Vision Language Learner).

MedViLL This repository provides the code for MedViLL(Medical Vision Language Learner). Our proposed architecture MedViLL is a single BERT-based model

SuperSuperMoon 39 Jan 05, 2023
Semantically Contrastive Learning for Low-light Image Enhancement

Semantically Contrastive Learning for Low-light Image Enhancement Here, we propose an effective semantically contrastive learning paradigm for Low-lig

48 Dec 16, 2022
Efficient neural networks for analog audio effect modeling

micro-TCN Efficient neural networks for audio effect modeling

Christian Steinmetz 94 Dec 29, 2022
Official code for paper "Optimization for Oriented Object Detection via Representation Invariance Loss".

Optimization for Oriented Object Detection via Representation Invariance Loss By Qi Ming, Zhiqiang Zhou, Lingjuan Miao, Xue Yang, and Yunpeng Dong. Th

ming71 56 Nov 28, 2022
Automatically erase objects in the video, such as logo, text, etc.

Video-Auto-Wipe Read English Introduction:Here   本人不定期的基于生成技术制作一些好玩有趣的算法模型,这次带来的作品是“视频擦除”方向的应用模型,它实现的功能是自动感知到视频中我们不想看见的部分(譬如广告、水印、字幕、图标等等)然后进行擦除。由于图标擦

seeprettyface.com 141 Dec 26, 2022
Six - a Python 2 and 3 compatibility library

Six is a Python 2 and 3 compatibility library. It provides utility functions for smoothing over the differences between the Python versions with the g

Benjamin Peterson 919 Dec 28, 2022
PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA

Soft DTW Loss Function for PyTorch in CUDA This is a Pytorch Implementation of Soft-DTW: a Differentiable Loss Function for Time-Series which is batch

Keon Lee 76 Dec 20, 2022
A simple pygame dino game which can also be trained and played by a NEAT KI

Dino Game AI Game The game itself was developed with the Pygame module pip install pygame You can also play it yourself by making the dino jump with t

Kilian Kier 7 Dec 05, 2022
nfelo: a power ranking, prediction, and betting model for the NFL

nfelo nfelo is a power ranking, prediction, and betting model for the NFL. Nfelo take's 538's Elo framework and further adapts it for the NFL, hence t

6 Nov 22, 2022
Does Oversizing Improve Prosumer Profitability in a Flexibility Market? - A Sensitivity Analysis using PV-battery System

Does Oversizing Improve Prosumer Profitability in a Flexibility Market? - A Sensitivity Analysis using PV-battery System The possibilities to involve

Babu Kumaran Nalini 0 Nov 19, 2021
Official implementation of the paper 'High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network' in CVPR 2021

LPTN Paper | Supplementary Material | Poster High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network Ji

372 Dec 26, 2022