Generalized out-of-distribution detection: A survey
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 …
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
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 …
of intelligent control and management systems, promising to change the future of artificial …
Provable guarantees for understanding out-of-distribution detection
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 …
models in the real world, where test data from shifted distributions can naturally arise. While …
A survey on learning to reject
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 …
know), which is an essential factor for humans to become smarter. Although machine …
Out-of-distribution detection learning with unreliable out-of-distribution sources
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 …
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
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 …
that their contents differ from all legal classes in terms of semantics, namely semantic …
Out-of-distribution detection in classifiers via generation
By design, discriminatively trained neural network classifiers produce reliable predictions
only for in-distribution samples. For their real-world deployments, detecting out-of …
only for in-distribution samples. For their real-world deployments, detecting out-of …
Out-of-distribution detection with semantic mismatch under masking
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 …
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
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 …
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 …
with test data drawn from a distribution different to that of the training data, constituting a …