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

04/06/2022
by   Umar Khalid, et al.
0

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 paper, 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 robustify the model, we empirically show that a pre-trained model with self-supervised contrastive learning yields a better model for uni-dimensional feature learning in the latent space. The method proposed in this work referred to as \texttt{RODD}, outperforms SOTA detection performance on an extensive suite of benchmark datasets on OOD detection tasks. On the CIFAR-100 benchmarks, RODD achieves a 26.97% lower false-positive rate (FPR@95) compared to SOTA methods

READ FULL TEXT
research
02/08/2022

Self-supervised Contrastive Learning for Volcanic Unrest Detection

Ground deformation measured from Interferometric Synthetic Aperture Rada...
research
03/19/2022

No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection

Unsupervised Anomaly detection (AD) requires building a notion of normal...
research
02/06/2023

Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness

Trustworthy machine learning is of primary importance to the practical d...
research
11/24/2021

ReAct: Out-of-distribution Detection With Rectified Activations

Out-of-distribution (OOD) detection has received much attention lately d...
research
06/07/2021

Multi-task Transformation Learning for Robust Out-of-Distribution Detection

Detecting out-of-distribution (OOD) samples plays a key role in open-wor...
research
05/31/2021

Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning

How can neural networks trained by contrastive learning extract features...
research
07/02/2023

End-to-End Out-of-distribution Detection with Self-supervised Sampling

Out-of-distribution (OOD) detection empowers the model trained on the cl...

Please sign up or login with your details

Forgot password? Click here to reset