cs.LGNov 4, 2026

Attraction-Ranking Mismatch in Out-of-Distribution Detection: Theory and Evidence from Hamiltonian Feature Dynamics

Authors: Zilin Wang, Lianghai Xiao

Organizations: School of Information Science and Technology, Jinan University, Guangzhou, 510632, China

Abstract

Attracting features toward learned in-distribution (ID) regions is an intuitive strategy for out-of-distribution (OOD) detection, but does such attraction improve detection? We investigate this question using class-conditioned Hamiltonian dynamics as a controlled testbed and identify an attraction-ranking mismatch: improving individual class-affinity scores need not improve the relative ordering of ID and OOD samples. Our analysis separates misalignment between the driving field and the detection score from ranking failure that persists even when they are aligned. An exact AUROC decomposition and a local boundary analysis identify relative score changes at the ID-OOD ranking boundary as the source of first-order AUROC change under regularity conditions. Experiments demonstrate that a score-aligned rule can improve performance on a held-out source validation split yet consistently degrade it after transfer, even without a single winning-class change. A separate perturbation study finds that near-boundary relative score changes track the direction of small AUROC changes in the tested settings. Finally, centroid approximation and shared scales connect the zero-step score to a static centroid family that includes the existing CTM detector. Together, these results explain why class attraction is insufficient to justify feature refinement and motivate evaluating its effect on the ranking boundary.

Figures & tables

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 19, 2026

TriScore: Post-Hoc Out-of-Distribution Detection with Energy, Boundary Probes, and Transform Consistency

Post-hoc out-of-distribution detection usually relies on a single signal extracted from a frozen classifier, such as confidence, energy, features, or gradients. This dependence becomes fragile under classifier-level adversarial shift, where the shift can preserve the detector's chosen cue while changing the model's decision behavior. We investigate whether this failure mode can be mitigated by combining complementary detection criteria instead of selecting a single score. We introduce TriScore, a post-hoc OOD detector that combines three ID-calibrated signals from the same frozen backbone: an energy prior, a boundary-fragility score, and a transform-consistency score. These signals are standardized on ID validation data and fused by an input-dependent ID-residual gate, requiring no OOD labels, auxiliary model, training, or stored feature bank. Across four ImageNet-scale backbones, TriScore achieves the best mean AUROC among 15 post-hoc baselines under a non-adaptive adversarial-shift protocol, while remaining competitive on standard OOD benchmarks. Ablations show that the gains come from combining complementary cues rather than optimizing a single detector signal. These results support multi-criterion post-hoc detection as a practical route toward more robust OOD detection under classifier-level shift. The source code is publicly available at github.com/gursoyege/TriScore.
Mar 18, 2026

CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring

Out-of-distribution (OOD) detection is essential for deploying deep learning models reliably, yet no single method performs consistently across architectures and datasets -- a scorer that leads on one benchmark often falters on another. We attribute this inconsistency to a shared structural limitation: logit-based methods see only the classifier's confidence signal, while feature-based methods attempt to measure membership in the training distribution but do so in the full feature space where confidence and membership are entangled, inheriting architecture-sensitive failure modes. We observe that penultimate features naturally decompose into two orthogonal subspaces: a classifier-aligned component encoding confidence, and a residual the classifier discards. We discover that this residual carries a class-specific directional signature for in-distribution data -- a membership signal invisible to logit-based methods and entangled with noise in feature-based methods. We propose CORE (COnfidence + REsidual), which disentangles the two signals by scoring each subspace independently and combines them via normalized summation. Because the two signals are orthogonal by construction, their failure modes are approximately independent, producing robust detection where either view alone is unreliable. CORE achieves competitive or state-of-the-art performance across five architectures and five benchmark configurations, ranking first in three of five settings and achieving the highest grand average AUROC with negligible computational overhead.
Nov 4, 2026

Don't Replace, Complement: A Detector-Agnostic Subspace Signal for Near-OOD Detection

Post-hoc out-of-distribution (OOD) detection is mature on far-OOD yet remains weak on near-OOD. These two settings differ in their use of class-characteristic feature directions: far-OOD inputs largely fail to activate those of their predicted class, whereas near-OOD inputs activate them much as in-distribution samples do. Because the axis separating far-OOD leaves near-OOD almost indistinguishable from ID, a score optimized for one setting is misaligned with the other; where a detector already saturates far-OOD, added near-OOD sensitivity is bought partly against it. This divergence motivates a targeted near-OOD signal designed to complement existing scores. We propose PLUS (Per-class Low-dimensional sUbspace Signal). For each class, PLUS selects the mm most class-active neurons from a sparse autoencoder, orthonormalizes the corresponding decoder directions to form a low-dimensional subspace, and scores an input by its per-class whitened squared Mahalanobis distance zz within the subspace of its predicted class. Designed as a dedicated complement rather than a standalone detector, the signal zz is fused additively with any calibrated base score at a single, fixed weight. This weight is a single global constant: no value is adjusted per backbone, per OOD dataset, or per deployment, and all calibration statistics are estimated from ID validation data alone. When applied to 18 existing detectors spanning diverse method families, zz consistently improves near-OOD AUROC in all 126 detector--backbone combinations. Far-OOD performance is broadly maintained or improved, with only marginal declines where the base score is near-optimal, making zz a robust, detector-agnostic complement across backbones.