Shifting Transformation Learning for Robust Out-of-Distribution Detection
Sina Mohseni (NVIDIA),* Arash Vahdat (NVIDIA), Jay Yadawa (NVIDIA)
The 33rd British Machine Vision Conference
Abstract
Detecting out-of-distribution (OOD) samples plays a key role in open-world and safety-critical applications such as autonomous systems and healthcare. Self-supervised representation learning techniques (e.g., contrastive learning and pretext learning) are well suited for learning representation that can identify OOD samples. In this paper, we propose a simple framework that leverages \textit{multi-task transformation learning} for training effective representation for OOD detection which outperforms state-of-the-art OOD detection performance and robustness on several image datasets. We empirically observe that the OOD performance depends on the choice of data transformations which itself depends on the in-domain training set. To address this problem, we propose a simple mechanism for selecting the transformations automatically and modulate their effect on representation learning without requiring any OOD training samples. We characterize the criteria for a desirable OOD detector for real-world applications and demonstrate the efficacy of our proposed technique against a diverse range of the state-of-the-art OOD detection techniques.Citation
@inproceedings{Mohseni_2022_BMVC,
author = {Sina Mohseni and Arash Vahdat and Jay Yadawa},
title = {Shifting Transformation Learning for Robust Out-of-Distribution Detection},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0679.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by