Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning — Paper

Abstract

In out-of-distribution (OOD) detection, fine-tuning with auxiliary outlier data often improves detection performance at the cost of classification accuracy. This trade-off stems from the loss of the original in-distribution (ID) distribution during fine-tuning. To establish a more practical and effective paradigm, we optimize three critical factors: model reminder, data sampling, and representation learning. We propose: (1) Self-Knowledge Distillation (SKD) to mitigate accuracy reduction; (2) Semi-hard Outlier Sampling (SOS) to improve detection efficiency with minimal data; and (3) Outlier-aware Supervised Contrastive Learning (OSCL) to promote ID-OOD separability. Optimizing these factors produces cumulative gains, boosting both OOD detection performance and classification accuracy. Our framework outperforms existing methods across diverse benchmarks, particularly in long-tailed scenarios, providing a robust baseline for real-world OOD detection.

Authors 3

Hyunjun Choi, JaeHo Chung, Hawook Jeong

Specification

Official page: arxiv.org/abs/2308.01030
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Arxiv announce type: replace
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
arXiv id: 2308.01030
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Categories: cs.LG, cs.AI, cs.CV
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
DOI: 10.1007/978-3-032-31930-2_29
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
PDF: arxiv.org/pdf/2308.01030
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Primary category: cs.LG
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

10

Source tiers

T110

Freshest observation

7 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Hyunjun Choi, JaeHo Chung, Hawook Jeong

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · DOI

1 claims · 1 propertiesShow all properties

DOIdoi1

Claim history for DOI
Value	Valid from → to	Status	Source	Confidence	Extractor
10.1007/978-3-032-31930-2_29	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperOptimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning
New paper: Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.LG	feed	T1· Official	5 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.