Source code for the project OOD Detection of COVID-19 From Chest X-Ray Images, written as part of the KTH course DD2424, Deep Learning in Data Science:
-
Updated
May 20, 2020 - Python
Source code for the project OOD Detection of COVID-19 From Chest X-Ray Images, written as part of the KTH course DD2424, Deep Learning in Data Science:
Self-Supervised Learning for OOD Detection (NeurIPS 2019)
Code for Paper: Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
Feature Space Singularity for Out-of-Distribution Detection. (SafeAI 2021)
Student project regarding out-of-domain text classification methods comparison on CLINC150 dataset.
Project Code for ICML UDL Workshop 2021 Submission
Code for "BayesAdapter: Being Bayesian, Inexpensively and Robustly, via Bayeisan Fine-tuning"
Source code for 《Energy-based Unknown Intent Detection with Data Manipulation》, which is accepted by Findings of ACL, 2021.
Baseline for out-of-distribution detection
We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness of OOD detection to various types of adversarial OOD inputs and establishes state-of-the-art performance.
The Official Implementation of the ICCV-2021 Paper: Semantically Coherent Out-of-Distribution Detection.
Robust Out-of-distribution Detection in Neural Networks
A re-implementation project of Serra et al.: “Input complexity and out-of-distribution detection with likelihood-based generative models"
Post-hoc Out-of-Distribution Detection
[Under Progress] Code & Data for the AAAI 2020 Paper "Likelihood Ratios and Generative Classifiers For Unsupervised OOD Detection In Task-Based Dialog" - Varun Gangal, Abhinav Arora, Arash Einolghozati, Sonal Gupta
A project to add scalable state-of-the-art out-of-distribution detection (open set recognition) support by changing two lines of code! Perform efficient inferences (i.e., do not increase inference time) and detection without classification accuracy drop, hyperparameter tuning, or collecting additional data.
A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in your project! Perform efficient inferences (i.e., do not increase inference time) without repetitive model training, hyperparameter tuning, or collecting additional data.
Tensorflow Implementation of various post hoc OOD detectors
Add a description, image, and links to the ood-detection topic page so that developers can more easily learn about it.
To associate your repository with the ood-detection topic, visit your repo's landing page and select "manage topics."