Generalized out-of-distribution detection: A survey

J Yang, K Zhou, Y Li, Z Liu - International Journal of Computer Vision, 2024 - Springer
Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Information theoretic learning-enhanced dual-generative adversarial networks with causal representation for robust OOD generalization

X Zhou, X Zheng, T Shu, W Liang… - … on Neural Networks …, 2023 - ieeexplore.ieee.org
Recently, machine/deep learning techniques are achieving remarkable success in a variety
of intelligent control and management systems, promising to change the future of artificial …

Provable guarantees for understanding out-of-distribution detection

P Morteza, Y Li - Proceedings of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
Abstract Out-of-distribution (OOD) detection is important for deploying machine learning
models in the real world, where test data from shifted distributions can naturally arise. While …

A survey on learning to reject

XY Zhang, GS **e, X Li, T Mei… - Proceedings of the IEEE, 2023 - ieeexplore.ieee.org
Learning to reject is a special kind of self-awareness (the ability to know what you do not
know), which is an essential factor for humans to become smarter. Although machine …

Out-of-distribution detection learning with unreliable out-of-distribution sources

H Zheng, Q Wang, Z Fang, X **a… - Advances in Neural …, 2023 - proceedings.neurips.cc
Abstract Out-of-distribution (OOD) detection discerns OOD data where the predictor cannot
make valid predictions as in-distribution (ID) data, thereby increasing the reliability of open …

Diffguard: Semantic mismatch-guided out-of-distribution detection using pre-trained diffusion models

R Gao, C Zhao, L Hong, Q Xu - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Given a classifier, the inherent property of semantic Out-of-Distribution (OOD) samples is
that their contents differ from all legal classes in terms of semantics, namely semantic …

Out-of-distribution detection in classifiers via generation

S Vernekar, A Gaurav, V Abdelzad, T Denouden… - arxiv preprint arxiv …, 2019 - arxiv.org
By design, discriminatively trained neural network classifiers produce reliable predictions
only for in-distribution samples. For their real-world deployments, detecting out-of …

Out-of-distribution detection with semantic mismatch under masking

Y Yang, R Gao, Q Xu - European Conference on Computer Vision, 2022 - Springer
This paper proposes a novel out-of-distribution (OOD) detection framework named MoodCat
for image classifiers. MoodCat masks a random portion of the input image and uses a …

SAFE: Sensitivity-aware features for out-of-distribution object detection

S Wilson, T Fischer, F Dayoub… - Proceedings of the …, 2023 - openaccess.thecvf.com
We address the problem of out-of-distribution (OOD) detection for the task of object
detection. We show that residual convolutional layers with batch normalisation produce …

Bayesian variational autoencoders for unsupervised out-of-distribution detection

E Daxberger, JM Hernández-Lobato - arxiv preprint arxiv:1912.05651, 2019 - arxiv.org
Despite their successes, deep neural networks may make unreliable predictions when faced
with test data drawn from a distribution different to that of the training data, constituting a …