OCO mitigates simplicity bias in OOD detection by predicting disentangled representations, dividing patterns into three co-occurrence scenarios from ID data, and applying divide-and-conquer detection.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
HCM turns neural outputs into magnitude plus unit hypersphere vector and treats uncertainty as the geometric violation of that unit constraint, yielding deterministic estimates for regression and classification that match ensembles at lower cost.
Sparse autoencoders on ViT class tokens reveal stable Class Activation Profiles for in-distribution data, enabling OOD detection via divergence from core energy profiles.
OS-DRE performs score-based density ratio estimation in one step by approximating the temporal score component with a closed-form RBF frame and providing error bounds from approximation theory.
ROSS combines median smoothing with local instability measurement to create a robust OOD detector that outperforms prior methods by up to 40 AUROC points on CIFAR and ImageNet benchmarks while defending symmetrically against score attacks.
VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.
citing papers explorer
-
Divide and Conquer: Object Co-occurrence Helps Mitigate Simplicity Bias in OOD Detection
OCO mitigates simplicity bias in OOD detection by predicting disentangled representations, dividing patterns into three co-occurrence scenarios from ID data, and applying divide-and-conquer detection.
-
Uncertainty Estimation via Hyperspherical Confidence Mapping
HCM turns neural outputs into magnitude plus unit hypersphere vector and treats uncertainty as the geometric violation of that unit constraint, yielding deterministic estimates for regression and classification that match ensembles at lower cost.
-
Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection
Sparse autoencoders on ViT class tokens reveal stable Class Activation Profiles for in-distribution data, enabling OOD detection via divergence from core energy profiles.
-
One-Step Score-Based Density Ratio Estimation
OS-DRE performs score-based density ratio estimation in one step by approximating the temporal score component with a closed-form RBF frame and providing error bounds from approximation theory.
-
A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing
ROSS combines median smoothing with local instability measurement to create a robust OOD detector that outperforms prior methods by up to 40 AUROC points on CIFAR and ImageNet benchmarks while defending symmetrically against score attacks.
-
VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning
VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.