Cover Image

Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peng, Ningkang, Chen, Xuanming, Gu, Yanhui
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
by: Peng, Ningkang, et al.
Published: (2026)

How to Achieve Prototypical Birth and Death for OOD Detection?
by: Peng, Ningkang, et al.
Published: (2026)

Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
by: Peng, Ningkang, et al.
Published: (2026)

Early High-Frequency Injection for Geometry-Sensitive OOD Detection
by: Cheng, Chuanjie, et al.
Published: (2026)

When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
by: Peng, Ningkang, et al.
Published: (2026)

A Geometry-Based View of Mahalanobis OOD Detection
by: Janiak, Denis, et al.
Published: (2025)

Breaking Semantic Hegemony: Decoupling Principal and Residual Subspaces for Generalized OOD Detection
by: Peng, Ningkang, et al.
Published: (2026)

Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
by: Mao, Jingyang, et al.
Published: (2026)

Mahalanobis++: Improving OOD Detection via Feature Normalization
by: Mueller, Maximilian, et al.
Published: (2025)

3D-CSAD: Untrained 3D Anomaly Detection for Complex Manufacturing Surfaces
by: Cao, Xuanming, et al.
Published: (2024)

Halt the Hallucination: Decoupling Signal and Semantic OOD Detection Based on Cascaded Early Rejection
by: Peng, Ningkang, et al.
Published: (2026)

TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection
by: Jung, Yoon Gyo, et al.
Published: (2025)

$Δ\mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
by: Zhu, Lin, et al.
Published: (2025)

Comprehensive OOD Detection Improvements
by: Lakkapragada, Anish, et al.
Published: (2024)

Evaluating Reliability in Medical DNNs: A Critical Analysis of Feature and Confidence-Based OOD Detection
by: Anthony, Harry, et al.
Published: (2024)

General-Purpose Multi-Modal OOD Detection Framework
by: Duong, Viet, et al.
Published: (2023)

Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
by: Feng, Shuai, et al.
Published: (2025)

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
by: Zhang, Lilin, et al.
Published: (2026)

How to train your ViT for OOD Detection
by: Mueller, Maximilian, et al.
Published: (2024)

Negative Label Guided OOD Detection with Pretrained Vision-Language Models
by: Jiang, Xue, et al.
Published: (2024)

Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
by: Duan, Chen-Long, et al.
Published: (2024)

GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibility
by: Abrahao, Bruno
Published: (2026)

Detecting OOD Samples via Optimal Transport Scoring Function
by: Gao, Heng, et al.
Published: (2025)

AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection
by: Yang, Puning, et al.
Published: (2023)

SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection
by: Tran, Phi Vu
Published: (2024)

CMOOD: Concept-based Multi-label OOD Detection
by: Liu, Zhendong, et al.
Published: (2024)

OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
by: Zhang, Jingyang, et al.
Published: (2023)

ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training
by: Colussi, Marco, et al.
Published: (2024)

Learning from Reduced Labels for Long-Tailed Data
by: Wei, Meng, et al.
Published: (2024)

Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD Detection
by: Singhal, Rishi, et al.
Published: (2024)

Feature Purified Transformer With Cross-level Feature Guiding Decoder For Multi-class OOD and Anomaly Deteciton
by: Lin, Jerry Chun-Wei, et al.
Published: (2024)

Can OOD Object Detectors Learn from Foundation Models?
by: Liu, Jiahui, et al.
Published: (2024)

Long-Tail Learning with Rebalanced Contrastive Loss
by: De Alvis, Charika, et al.
Published: (2023)

NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection
by: Ansari, Amirhossein, et al.
Published: (2025)

Adaptive Residual Transformation for Enhanced Feature-Based OOD Detection in SAR Imagery
by: Lee, Kyung-hwan, et al.
Published: (2024)

DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition
by: Baik, Jae Soon, et al.
Published: (2022)

Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles
by: Peng, Shuman, et al.
Published: (2024)

Solution for OOD-CV Workshop SSB Challenge 2024 (Open-Set Recognition Track)
by: Feng, Mingxu, et al.
Published: (2024)

Scalable Ensemble Diversification for OOD Generalization and Detection
by: Rubinstein, Alexander, et al.
Published: (2024)

DELTA: Decoupling Long-Tailed Online Continual Learning
by: Raghavan, Siddeshwar, et al.
Published: (2024)