RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection

Related tags

Deep LearningRODD
Overview

RODD Official Implementation of 2022 CVPRW Paper

RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection

Introduction: Recent studies have addressed the concern of detecting and rejecting the out-of-distribution (OOD) samples as a major challenge in the safe deployment of deep learning (DL) models. It is desired that the DL model should only be confident about the in-distribution (ID) data which reinforces the driving principle of the OOD detection. In this work, we propose a simple yet effective generalized OOD detection method independent of out-of-distribution datasets. Our approach relies on self-supervised feature learning of the training samples, where the embeddings lie on a compact low-dimensional space. Motivated by the recent studies that show self-supervised adversarial contrastive learning helps robustifying the model, we empirically show that a pre-trained model with selfsupervised contrastive learning yields a better model for uni-dimensional feature learning in the latent space. The method proposed in this work, referred to as RODD, outperforms SOTA detection performance on extensive suite of benchmark datasets on OOD detection tasks. pipeline Overall architecture of the proposed OOD detection method. (a) In the first step, self-supervised adversarial contrastive learning is performed.(b) Secondly, the encoder is fine-tuned by freezing the weights of the penultimate layer. (c) Thirdly, we calculate the first singular vectors of each class using their features. (d) The final step is the OOD detection where uncertainty score is estimated using cosine similarity between the feature vector of the test sample and first singular vectors of each ID class.

Dataset Preparation

In-Distribution Datasets

CIFAR-10 and CIFAR-100 are in-distribution datasets which will be automatically downloaded during training

OOD Datasets

Create a folder 'data' in the root 'RODD' folder
Download following OOD datasets in the 'data' folder.
Places
Textures (Download the entire dataset)
All other OOD Datasets such as ImageNetc, ImageNetr, LSUNr, LSUNc, iSUN and SVHN can be downloaded from Google Drive

Running the Code

Tested on:

Python 3.9 cuda 11.2 torch 1.8.1 torchvision 0.9.1 numpy 1.20.1 sklearn 0.24.1

Pre-Training

For CIFAR-10:

python pretrain.py --dataset cifar10

For CIFAR-100:

python pretrain.py --dataset cifar100

Fine-Tuning

For CIFAR-10:

python fine_tune.py --dataset cifar10

For CIFAR-100:

python fine_tune.py --dataset cifar100

Evaluation

For CIFAR-10:

python extract_features in-dataset cifar10
python evaluate_original

For CIFAR-100:

python extract_features in-dataset cifar100
python evaluate_original

Citation

@misc{https://doi.org/10.48550/arxiv.2204.02553,
  doi = {10.48550/ARXIV.2204.02553},
  url = {https://arxiv.org/abs/2204.02553},
  author = {Khalid, Umar and Esmaeili, Ashkan and Karim, Nazmul and Rahnavard, Nazanin},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}
Owner
Umar Khalid
I am a Comp. Engineering Ph.D. student at the University of Central Florida, USA.
Umar Khalid
The implemetation of Dynamic Nerual Garments proposed in Siggraph Asia 2021

DynamicNeuralGarments Introduction This repository contains the implemetation of Dynamic Nerual Garments proposed in Siggraph Asia 2021. ./GarmentMoti

42 Dec 27, 2022
Find-Lane-Line - Use openCV library and Python to detect the road-lane-line

Find-Lane-Line This project is to use openCV library and Python to detect the road-lane-line. Data Pipeline Step one : Color Selection Step two : Cann

Kenny Cheng 3 Aug 17, 2022
Towards Boosting the Accuracy of Non-Latin Scene Text Recognition

Convolutional Recurrent Neural Network + CTCLoss | STAR-Net Code for paper "Towards Boosting the Accuracy of Non-Latin Scene Text Recognition" Depende

Sanjana Gunna 7 Aug 07, 2022
Official code for paper "Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight"

Demysitifing Local Vision Transformer, arxiv This is the official PyTorch implementation of our paper. We simply replace local self attention by (dyna

138 Dec 28, 2022
A fast and easy to use, moddable, Python based Minecraft server!

PyMine PyMine - The fastest, easiest to use, Python-based Minecraft Server! Features Note: This list is not always up to date, and doesn't contain all

PyMine 144 Dec 30, 2022
DABO: Data Augmentation with Bilevel Optimization

DABO: Data Augmentation with Bilevel Optimization [Paper] The goal is to automatically learn an efficient data augmentation regime for image classific

ElementAI 24 Aug 12, 2022
ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

ESRGAN (Enhanced SRGAN) [ 🚀 BasicSR] [Real-ESRGAN] ✨ New Updates. We have extended ESRGAN to Real-ESRGAN, which is a more practical algorithm for rea

Xintao 4.7k Jan 02, 2023
The deployment framework aims to provide a simple, lightweight, fast integrated, pipelined deployment framework that ensures reliability, high concurrency and scalability of services.

savior是一个能够进行快速集成算法模块并支持高性能部署的轻量开发框架。能够帮助将团队进行快速想法验证(PoC),避免重复的去github上找模型然后复现模型;能够帮助团队将功能进行流程拆解,很方便的提高分布式执行效率;能够有效减少代码冗余,减少不必要负担。

Tao Luo 125 Dec 22, 2022
Kaggle-titanic - A tutorial for Kaggle's Titanic: Machine Learning from Disaster competition. Demonstrates basic data munging, analysis, and visualization techniques. Shows examples of supervised machine learning techniques.

Kaggle-titanic This is a tutorial in an IPython Notebook for the Kaggle competition, Titanic Machine Learning From Disaster. The goal of this reposito

Andrew Conti 800 Dec 15, 2022
Data pipelines for both TensorFlow and PyTorch!

rapidnlp-datasets Data pipelines for both TensorFlow and PyTorch ! If you want to load public datasets, try: tensorflow/datasets huggingface/datasets

1 Dec 08, 2021
Recursive Bayesian Networks

Recursive Bayesian Networks This repository contains the code to reproduce the results from the NeurIPS 2021 paper Lieck R, Rohrmeier M (2021) Recursi

Robert Lieck 11 Oct 18, 2022
Lighting the Darkness in the Deep Learning Era: A Survey, An Online Platform, A New Dataset

Lighting the Darkness in the Deep Learning Era: A Survey, An Online Platform, A New Dataset This repository provides a unified online platform, LoLi-P

Chongyi Li 457 Jan 03, 2023
This is the code for the paper "Contrastive Clustering" (AAAI 2021)

Contrastive Clustering (CC) This is the code for the paper "Contrastive Clustering" (AAAI 2021) Dependency python=3.7 pytorch=1.6.0 torchvision=0.8

Yunfan Li 210 Dec 30, 2022
[NeurIPS 2021] Low-Rank Subspaces in GANs

Low-Rank Subspaces in GANs Figure: Image editing results using LowRankGAN on StyleGAN2 (first three columns) and BigGAN (last column). Low-Rank Subspa

112 Dec 28, 2022
A general-purpose encoder-decoder framework for Tensorflow

READ THE DOCUMENTATION CONTRIBUTING A general-purpose encoder-decoder framework for Tensorflow that can be used for Machine Translation, Text Summariz

Google 5.5k Jan 07, 2023
Deep Convolutional Generative Adversarial Networks

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Alec Radford, Luke Metz, Soumith Chintala All images in t

Alec Radford 3.4k Dec 29, 2022
A practical ML pipeline for data labeling with experiment tracking using DVC.

Auto Label Pipeline A practical ML pipeline for data labeling with experiment tracking using DVC Goals: Demonstrate reproducible ML Use DVC to build a

Todd Cook 4 Mar 08, 2022
A `Neural = Symbolic` framework for sound and complete weighted real-value logic

Logical Neural Networks LNNs are a novel Neuro = symbolic framework designed to seamlessly provide key properties of both neural nets (learning) and s

International Business Machines 138 Dec 19, 2022
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.

openpifpaf Continuously tested on Linux, MacOS and Windows: New 2021 paper: OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Te

VITA lab at EPFL 50 Dec 29, 2022
[ACL-IJCNLP 2021] Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

CLNER The code is for our ACL-IJCNLP 2021 paper: Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning CLNER is a

71 Dec 08, 2022