MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Donghwan, Yoon, Hyunsoo
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mitigating the Likelihood Paradox in Flow-based OOD Detection via Entropy Manipulation
by: Kim, Donghwan, et al.
Published: (2026)

Why the Counterintuitive Phenomenon of Likelihood Rarely Appears in Tabular Anomaly Detection with Deep Generative Models?
by: Kim, Donghwan, et al.
Published: (2026)

Interpreting Neural Networks through Mahalanobis Distance
by: Oursland, Alan
Published: (2024)

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
by: Ray, Rahul D
Published: (2026)

Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies
by: Graf, Olga, et al.
Published: (2026)

Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance
by: Yoon, Heegeon, et al.
Published: (2026)

Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
by: Kim, Taehoon, et al.
Published: (2025)

Adaptive Policy Backbone via Shared Network
by: Park, Bumgeun, et al.
Published: (2025)

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

Taming the Adversary: Stable Minimax Deep Deterministic Policy Gradient via Fractional Objectives
by: Lee, Taeho, et al.
Published: (2026)

Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty
by: Kim, Jeonghyun, et al.
Published: (2026)

Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse
by: He, Kun, et al.
Published: (2025)

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
by: Mao, Yixiu, et al.
Published: (2024)

A Simple and Effective Method for Uncertainty Quantification and OOD Detection
by: Ma, Yaxin, et al.
Published: (2025)

Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulation
by: Kim, Donghwan, et al.
Published: (2026)

Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic Graphs
by: Sun, Nan, et al.
Published: (2025)

Backbone-Equated Diffusion OOD via Sparse Internal Snapshots
by: Rouzoumka, Yadang Alexis, et al.
Published: (2026)

Soft Deterministic Policy Gradient with Gaussian Smoothing
by: Na, Hyunjun, et al.
Published: (2026)

R-GTD: A Geometric Analysis of Gradient Temporal-Difference Learning in Singular Regimes
by: Na, Hyunjun, et al.
Published: (2026)

Preventing Model Collapse via Contraction-Conditioned Neural Filters
by: Han, Zongjian, et al.
Published: (2025)

Toward a Unified Lyapunov-Certified ODE Convergence Analysis of Smooth Q-Learning with p-Norms
by: Lee, Donghwan, et al.
Published: (2024)

Lyapunov-Certified Direct Switching Theory for Q-Learning
by: Lee, Donghwan
Published: (2026)

DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
by: Shing, Makoto, et al.
Published: (2025)

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

The Prevalence of Neural Collapse in Neural Multivariate Regression
by: Andriopoulos, George, et al.
Published: (2024)

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
by: Aguilar, Leonel, et al.
Published: (2026)

TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
by: Liu, Yuyang, et al.
Published: (2025)

Understanding the theoretical properties of projected Bellman equation, linear Q-learning, and approximate value iteration
by: Lim, Han-Dong, et al.
Published: (2025)

Analysis of Off-Policy $n$-Step TD-Learning with Linear Function Approximation
by: Lim, Han-Dong, et al.
Published: (2025)

Finite-Time Analysis of Temporal Difference Learning with Experience Replay
by: Lim, Han-Dong, et al.
Published: (2023)

Backstepping Temporal Difference Learning
by: Lim, Han-Dong, et al.
Published: (2023)

Suppressing Overestimation in Q-Learning through Adversarial Behaviors
by: Lee, HyeAnn, et al.
Published: (2023)

Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model
by: Cho, Hyunsoo
Published: (2024)

Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
by: Kim, Donghwan, et al.
Published: (2024)

Conditional Generative Framework with Peak-Aware Attention for Robust Chemical Detection under Interferences
by: Yoon, Namkyung, et al.
Published: (2026)

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
by: Park, Sangyeon, et al.
Published: (2025)

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training
by: Gwak, Minju, et al.
Published: (2026)

Safe-Support Q-Learning: Learning without Unsafe Exploration
by: Lim, Yeeun, et al.
Published: (2026)

Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
by: Park, Jongchan, et al.
Published: (2025)

From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection
by: Wang, Luzhi, et al.
Published: (2026)