FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.
hub
OpenOOD v1.5: Enhanced Benchmark for Out -of- Distribution Detection
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
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.
Catalyst improves OOD detection by multiplicatively scaling baseline scores using channel-wise statistics from pre-pooling feature maps, reducing average FPR by 22-33% on standard benchmarks.
HCM estimates uncertainty in neural network outputs by quantifying violation of a unit hypersphere constraint on the normalized direction vector.
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.
InterNeg improves OOD detection in VLMs by using inter-modal distance criteria for negative text selection and by inverting high-confidence OOD images into additional negative text embeddings.
CDPIR integrates cross-distribution diffusion priors from a Scalable Interpolant Transformer trained with classifier-free guidance into model-based iterative reconstruction to improve sparse-view CT under out-of-distribution conditions.
Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.
OCO uses object co-occurrence analysis to divide OOD detection into scenarios based on ID training data patterns for improved near-OOD performance.
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.
RankOOD detects out-of-distribution samples by training a model to predict fixed class-specific ranking permutations via the Plackett-Luce loss, achieving a 4.3% FPR95 reduction on near-OOD TinyImageNet.
Benchmark across architectures and shift regimes finds OOD detector rankings shift with representation collapse; proposes NC-based shortlist predictor and PCA filter without extra OOD data.
A new framework adds adaptive background patch suppression via entropy weighting and confusable foreground patch rectification to existing FG-BG methods, significantly improving few-shot OOD detection.
Post-hoc normalizing flows for OOD detection in medical imaging achieve 84.61% AUROC on MedOOD and 93.8% on MedMNIST, outperforming ViM, MDS, and ReAct.
citing papers explorer
-
FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.
-
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.
-
Catalyst: Out-of-Distribution Detection via Elastic Scaling
Catalyst improves OOD detection by multiplicatively scaling baseline scores using channel-wise statistics from pre-pooling feature maps, reducing average FPR by 22-33% on standard benchmarks.
-
Uncertainty Estimation via Hyperspherical Confidence Mapping
HCM estimates uncertainty in neural network outputs by quantifying violation of a unit hypersphere constraint on the normalized direction vector.
-
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.
-
Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs
InterNeg improves OOD detection in VLMs by using inter-modal distance criteria for negative text selection and by inverting high-confidence OOD images into additional negative text embeddings.
-
Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CT
CDPIR integrates cross-distribution diffusion priors from a Scalable Interpolant Transformer trained with classifier-free guidance into model-based iterative reconstruction to improve sparse-view CT under out-of-distribution conditions.
-
Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection
Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.
-
Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis
OCO uses object co-occurrence analysis to divide OOD detection into scenarios based on ID training data patterns for improved near-OOD performance.
-
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.
-
RankOOD -- Class Ranking-based Out-of-Distribution Detection
RankOOD detects out-of-distribution samples by training a model to predict fixed class-specific ranking permutations via the Plackett-Luce loss, achieving a 4.3% FPR95 reduction on near-OOD TinyImageNet.
-
A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts
Benchmark across architectures and shift regimes finds OOD detector rankings shift with representation collapse; proposes NC-based shortlist predictor and PCA filter without extra OOD data.
-
Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background
A new framework adds adaptive background patch suppression via entropy weighting and confusable foreground patch rectification to existing FG-BG methods, significantly improving few-shot OOD detection.
-
Safeguarding AI in Medical Imaging: Post-Hoc Out-of-Distribution Detection with Normalizing Flows
Post-hoc normalizing flows for OOD detection in medical imaging achieve 84.61% AUROC on MedOOD and 93.8% on MedMNIST, outperforming ViM, MDS, and ReAct.