arXiv research

Method enhances anomaly detection using contrastive learning and out-of-distribution data.

Simple methods combine statistical tests for out-of-distribution detection.

Bayesian Gaussian Processes layer detects out-of-distribution data in medical imaging.

Deep learning models are known to be overconfident in their predictions on out of distribution inputs. There have been several pieces of work to address this issue, including a number of approaches for building Bayesian neural networks, as well as closely related work on detection of out of distribution samples. Recent…

Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must determine whether or not an input is outside of the set on which it is expected to safel…

Combining Bayesian deep learning and split conformal prediction affects out-of-distribution coverage.

Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distrib…

XEnsemble improves DNN robustness against adversarial and out-of-distribution inputs.

Single deep model detects out-of-distribution data with single forward pass.

Unified study of out-of-distribution generalization across 172 datasets.

Deep learning models are known to be overconfident in their predictions on out of distribution inputs. This is a challenge when a model is trained on a particular input dataset, but receives out of sample data when deployed in practice. Recently, there has been work on building classifiers that are robust to out of dis…

The paper shows strong correlation between in-distribution and out-of-distribution performance in various machine learning models.

SLUG method detects bias and out-of-distribution content in generative models.

New framework detects out-of-distribution data by considering intrinsic ID attributes in outliers.

Study optimal ridge regularization for out-of-distribution prediction.

A simple method flags images as out-of-distribution based on their distance to nearest neighbors.

New methods predict language model out-of-distribution behaviors using causal mechanisms.

Bayesian framework improves deep classifier reliability.

Igeood detects out-of-distribution samples using information geometry.

In this work, we propose a method to reject out-of-distribution samples which can be adapted to any network architecture and requires no additional training data. Publicly available chest x-ray data (38,353 images) is used to train a standard ResNet-50 model to detect emphysema. Feature activations of intermediate laye…

Bayesian layer improves image segmentation and out-of-distribution detection.

Recent work has shown that deep generative models assign higher likelihood to out-of-distribution inputs than to training data. We show that a factor underlying this phenomenon is a mismatch between the nature of the prior distribution and that of the data distribution, a problem found in widely used deep generative mo…

The problem of detecting whether a test sample is from in-distribution (i.e., training distribution by a classifier) or out-of-distribution sufficiently different from it arises in many real-world machine learning applications. However, the state-of-art deep neural networks are known to be highly overconfident in their…

A new method approximates pNML for faster out-of-distribution detection.

Study complex-valued VAEs for radar OOD detection.

Novel neural network models quantify uncertainty for deep classifiers.

NECO detects out-of-distribution data using neural collapse properties.

PEOC uses policy entropy to detect untrained states in RL.

Normalizing flows fail to detect OOD data due to learning local pixel correlations.

GRAM enhances deep RL for reliable real-world deployment.

CGD improves diffusion models' out-of-distribution generalization.

A new operator based on t-distributions improves NN classifiers' robustness to out-of-distribution samples.

Modern deep artificial neural networks have achieved great success in the domain of computer vision and beyond. However, their application to many real-world tasks is undermined by certain limitations, such as overconfident uncertainty estimates on out-of-distribution data or performance deterioration under data distri…

Regularizes ML algorithms for robust multivariate analysis against distribution shifts.

Sharp analysis of out-of-distribution error in overparameterized models with importance weights.

Hierarchical VAEs detect out-of-distribution data by identifying low-level in-distribution features.

Proposes training neural networks to predict uncertainty for out-of-distribution inputs.

GCRL learns causal factors for motion forecasting, improving out-of-distribution prediction.

ACNML method improves uncertainty estimation for deep networks.

Accuracy on in-distribution data correlates with out-of-distribution data when data is noisy or contains nuisance features.

Study shows LLMs can extrapolate rules from out-of-distribution prompts.

Research tackles ML failure in non-similar data, introducing reliable algorithms.

Quantum models learn unitary actions on entangled states from product states.

Improved VAE model enhances uncertainty estimation for out-of-distribution samples.

Novel conformal methods test out-of-distribution data with labeled outliers.

Graph convolution improves linear separability and generalizes to out-of-distribution data.

Paper fine-tunes a simulation-driven estimator to reduce out-of-distribution errors.

A new algorithm detects out-of-distribution samples by concentrating them in feature space.