GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibility
Bruno Abrahao

TL;DR
GEODE introduces an angle-adaptive norm loss for out-of-distribution detection, maintaining feature geometry and improving scorer performance across benchmarks without requiring curated auxiliary data.
Contribution
It provides a novel boundary calibration method that works universally with different scorers and outperforms existing OE-based methods on standard benchmarks.
Findings
GEODE achieves high AUROC scores on CIFAR-10 and CIFAR-100 benchmarks.
GEODE outperforms vanilla CE and OE on multiple scorers and datasets.
The method maintains feature geometry crucial for distance-based scoring.
Abstract
Outlier Exposure (OE) is among the strongest training-based OOD detectors on standard benchmarks but exhibits scorer-dependent tradeoffs (e.g., strong on MSP, weak on KNN) and requires curated auxiliary data. We show why OE works: its features sit at the same geometric locus as real near-OOD data, with the boundary-adjacent quartile driving nearly all of OE's gain. OE is boundary calibration, not OOD coverage. GEODE (GEOmetry-preserving DEtection) replicates this calibration synthetically through an angle-adaptive norm loss in which targets scale per-sample with cosine similarity to the nearest class mean, preserving feature geometry where boundary structure matters. Four theorems grounded in neural collapse justify the design. GEODE works across all seven standard scorers on CIFAR-10 (near-OOD AUROC 89.0-92.3, far-OOD reaching 93.05; no catastrophic failure on any scorer). Since the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
