MM++: Unsupervised Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion

• URL: http://arxiv.org/abs/2606.17352v1
• Date: Mon, 15 Jun 2026 22:52:54 GMT
• Title: MM++: Unsupervised Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion
• Abstract summary: MM++ is a fully unsupervised, strictly post-hoc, and scale-invariant framework for Out-of-Distribution (OOD) detection.<n>It first identifies discriminative intermediate layers by measuring entropy density drops, which mark the boundaries of sharp semantic compression.<n>By fusing these selected layers with the terminal representation, the framework captures latent cross-layer correlations while mitigating early-layer noise.
• Score: 0.4666493857924358
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce MM++ (Multilayer Mahalanobis++), a fully unsupervised, strictly post-hoc, and scale-invariant framework for Out-of-Distribution (OOD) detection. To address the trade-off between scale invariance and hierarchical expressivity, MM++ constructs a principled joint feature space. It first identifies discriminative intermediate layers by measuring entropy density drops, which mark the boundaries of sharp semantic compression. By fusing these selected layers with the terminal representation, the framework captures latent cross-layer correlations while mitigating early-layer noise. Crucially, a Ledoit-Wolf regularized tied covariance matrix stabilizes this unified space, enabling reliable distance estimation. Requiring no auxiliary OOD data, classifier fine-tuning, or architectural modifications, MM++ delivers robust performance across distinct architectures for both near- and far-OOD detection.

Related papers

• Layer Selection in VLMs for Zero-Shot OOD Detection via Multi-Resolution Entropy Estimation [6.633563728823828]
  Out-of-distribution (OOD) detection is crucial for safe deployment of medical AI systems.<n>We show that existing methods rely almost exclusively on final-layer embeddings, implicitly assuming that the deepest representations are universally optimal.<n>We propose a multi-resolution entropy estimation strategy that aggregates histogram statistics across multiple discretization scales.
  arXiv  Detail & Related papers  (2026-09-08T10:12:52Z)
• Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection [12.06155749281499]
  PRISM is a model-agnostic post-hoc OOD detection method.<n>It fuses intermediate and deep features into a single hierarchical embedding.<n>It captures both in-subspace semantic deviations and off-subspace anomalies.
  arXiv  Detail & Related papers  (2026-09-06T19:00:54Z)
• AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE [51.994752158953084]
  AnchorMoE is an interpretable-by-construction classification framework.<n>It encodes multi-view representations of local patches and routes them to specialized experts.<n>Experiments on real-world and synthetic benchmarks demonstrate that AnchorMoE achieves highly competitive classification performance.
  arXiv  Detail & Related papers  (2026-06-02T13:30:54Z)
• Inference Time Causal Probing in LLMs [26.69306706280534]
  In causal probing, an intervention modifies hidden states so that a property takes on a different value.<n>We propose Hidden-state Driven Margin Intervention (HDMI), a probe-free, gradient-based technique that directly steers hidden states.<n> HDMI consistently achieves higher reliability than prior methods on the LGD agreement corpus and the CausalGym benchmark.
  arXiv  Detail & Related papers  (2026-05-08T11:59:13Z)
• RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty [12.261505821589452]
  We propose a single-pass method that estimates prediction uncertainty by measuring mutual information between decoder layers in segmentation networks.<n>RADMI achieves the highest correlation with deep ensemble uncertainty among all single-pass methods.<n>Our results suggest that linear aggregation of normalized information flow provides a principled and efficient proxy for prediction uncertainty in encoder-decoder architectures.
  arXiv  Detail & Related papers  (2026-05-02T15:49:25Z)
• Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection [0.8394724589095839]
  We show that intermediate layers encode equally rich and discriminative information for OOD detection.<n>We propose a model-agnostic approach that leverages internal representations across multiple layers.<n>Our approach delivers robust, architecture-agnostic performance and strong generalization for image classification.
  arXiv  Detail & Related papers  (2026-03-24T19:32:13Z)
• MS-ISSM: Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similarity [65.85858856481131]
  unstructured and irregular nature of point clouds poses a significant challenge for objective quality assessment (PCQA)<n>We propose the Multi-scale Implicit Structural Similarity Measurement (MS-ISSM)
  arXiv  Detail & Related papers  (2026-01-03T14:58:52Z)
• GROOD: GRadient-Aware Out-of-Distribution Detection [11.511906612904255]
  Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications.<n>We propose GRadient-aware Out-Of-Distribution detection (GROOD), a method that derives an OOD prototype from synthetic samples and computes class prototypes directly from In-distribution (ID) training data.
  arXiv  Detail & Related papers  (2023-12-22T04:28:43Z)
• Detecting Out-of-Distribution Through the Lens of Neural Collapse [7.04686607977352]
  Out-of-Distribution (OOD) detection is critical for safe deployment.<n>Inspired by the phenomenon of Neural Collapse, we propose a versatile and efficient OOD detection method.
  arXiv  Detail & Related papers  (2023-11-02T05:18:28Z)
• Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data [77.27338842609153]
  characterization reveals that sensitivity to each type of shift is important to the detection and confidence calibration of OOD data. We propose a geometrically-inspired method to improve OOD detection under both shifts with only in-distribution data. We are the first to propose a method that works well across both OOD detection and calibration and under different types of shifts.
  arXiv  Detail & Related papers  (2021-10-28T15:42:55Z)
• Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty [58.144520501201995]
  Bi-Lipschitz regularization of neural network layers preserve relative distances between data instances in the feature spaces of each layer. With the use of an attentive set encoder, we propose to meta learn either diagonal or diagonal plus low-rank factors to efficiently construct task specific covariance matrices. We also propose an inference procedure which utilizes scaled energy to achieve a final predictive distribution.
  arXiv  Detail & Related papers  (2021-10-12T22:04:19Z)
• Multi-scale Interactive Network for Salient Object Detection [91.43066633305662]
  We propose the aggregate interaction modules to integrate the features from adjacent levels. To obtain more efficient multi-scale features, the self-interaction modules are embedded in each decoder unit. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-07-17T15:41:37Z)
• Scope Head for Accurate Localization in Object Detection [135.9979405835606]
  We propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO.
  arXiv  Detail & Related papers  (2020-05-11T04:00:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.