arXiv research

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

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. 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…

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

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

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…

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

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…

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

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…

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

Novel neural network models quantify uncertainty for deep classifiers.

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…

Real-time detection of out-of-distribution data in CPS control systems.

Bayesian framework improves deep classifier reliability.

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

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

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

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

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…

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

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

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

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

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

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

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

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

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

Counterfactual data augmentations may not ensure OOD robustness if performed by a context-guessing machine.

This paper improves normalizing flows by combining MLE and sliced-Wasserstein distance for better data fidelity.

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

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

Study complex-valued VAEs for radar OOD detection.

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

FOOD detects out-of-distribution samples quickly without needing OOD data.

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

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

Paper tackles SCOD problem with optimal strategy and empirical validation.

Paper aims to ensure reliable detection of out-of-distribution data with certifiable worst-case guarantees.

The effective application of neural networks in the real-world relies on proficiently detecting out-of-distribution examples. Contemporary methods seek to model the distribution of feature activations in the training data for adequately distinguishing abnormalities, and the state-of-the-art method uses Gaussian distrib…

Study on how kernel regression models generalize to out-of-distribution data.

A new principle for extrapolating regression outside training data.

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…

ProSub uses angles in feature space to classify data as in- or out-of-distribution.

EntProp increases entropy of clean samples to generate out-of-distribution data for better DNN performance.

Study compares data-driven vs model-based MRS quantification strategies, focusing on resilience to out-of-distribution effects.

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