Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2605.20502v1
• Date: Tue, 19 May 2026 21:18:49 GMT
• Title: Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection
• Abstract summary: We statistically identify each encoder's sensitivity to specific shift types from ID data alone.<n>We introduce EncMin2L -- an encoder-a two-level $min(cdot)$-gate that combines and calibrates per-encoder diffusion-based likelihood detectors.
• Score: 1.6921396880325779
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We address out-of-distribution (OOD) detection across the full spectrum of distribution shifts -- global domain changes, semantic divergence, texture differences, and covariate corruptions -- through a multi-encoder fusion of per-encoder representation-space diffusion models (RDMs). We statistically identify each encoder's sensitivity to specific shift types from ID data alone and introduce EncMin2L -- an encoder-agnostic two-level $\min(\cdot)$-gate that combines and calibrates per-encoder diffusion-based likelihood detectors without OOD labels, outperforming monolithic multi-encoder baselines at $2.3\times$ lower parameter cost. Two ID-data diagnostics: $η^2$ (class-conditional F-test) and $Δμ$ (log-likelihood shift under synthetic corruptions) -- quantify encoder specialization, while a Tippett minimum $p$-value combination aggregates per-encoder scores into a single, calibration-stable OOD signal. EncMin2L achieves $\geq 0.94$ AUROC across all four shift types simultaneously, outperforming the state-of-the-art representation-space diffusion OOD detectors across overlapping benchmarks.

Related papers

• Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data [0.5213778368155993]
  DIFFINT is an autoencoder whose latent bottleneck is structured as a set of soft, axis-aligned interval memberships.<n>It is the only interpretable detector in the statistically-tied leading cluster of seven methods.
  arXiv  Detail & Related papers  (2026-09-03T14:05:27Z)
• Level, Sharpness, and Corpus: Why Zero-Shot OOD Detector Rankings Do Not Transfer [36.02174685737611]
  We find that detector rankings reverse across deployments, every detector exceeds $80%$ FPR95 on at least one domain, and the preferred detector depends on both the in-distribution data and the underlying VLM.<n>We introduce the Complementary Evidence Guard (CEG), a detector-agnostic wrapper that preserves complementary evidence through a non-compensatory fusion of the base detector, level, and sharpness.
  arXiv  Detail & Related papers  (2026-07-29T08:00:49Z)
• An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers [0.0]
  Transformers consuming multi-channel scalar signals must embed $C$ simultaneous values into one $d_textmodel$-dimensional vector per time step.<n>We audit eight input encoders -- a shared-scalar baseline, per-channel linear projections, an explicit regulariser, a nonlinearoretic, block-partitioned concatenation, channel-independent and channel-as-token.<n>We find that the standard per-channel linear projection matches every alternative up to small, statistically real but practically modest differences.
  arXiv  Detail & Related papers  (2026-06-03T11:35:09Z)
• Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs [50.3757247538081]
  We retrain and evaluate all 31 non-empty subsets of five common vision encoders under a unified pipeline.<n>We decompose each encoder's contribution into two axes, Capacity and Necessity.<n>Per-encoder pre-projector effective rank explains the residual score variation.
  arXiv  Detail & Related papers  (2026-06-02T16:46:42Z)
• Bin Latent Transformer (BiLT): A shift-invariant autoencoder for calibration-free spectral unmixing of turbid media [0.0]
  This work introduces the Bin Latent Transformer (BiLT)-Autoencoder, in which the dense encoder is replaced by a cross-attention scanner.<n>A physics-constrained linear decoder with enforced absorption/scattering separation and a three-phase curriculum augmentation strategy completes the architecture.
  arXiv  Detail & Related papers  (2026-05-12T09:17:43Z)
• Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors [0.17398560678845076]
  We propose an evolutionary multi-objective score fusion framework that jointly minimizes detection error and system complexity.<n>Experiments on the ASVspoof 5 dataset with 36 SSL-based detectors show that the obtained fronts outperform simple averaging and logistic regression baselines.<n>Our method also provides a diverse set of trade-off solutions, enabling deployment choices that balance accuracy and computational cost.
  arXiv  Detail & Related papers  (2026-04-01T19:17:59Z)
• Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders [54.03921875874111]
  We show that performance degrades gracefully when selected encoders are masked, revealing pervasive encoder redundancy.<n>We observe strong specialization on tasks like OCR and Chart, where a single encoder can dominate with a CUR greater than 90%.<n>Masking specific encoders can yield up to 16% higher accuracy on a specific task category and 3.6% overall performance boost compared to the full model.
  arXiv  Detail & Related papers  (2025-07-04T02:38:59Z)
• Threshold Selection for Iterative Decoding of $(v,w)$-regular Binary Codes [84.0257274213152]
  Iterative bit flipping decoders are an efficient choice for sparse $(v,w)$-regular codes.<n>We propose concrete criteria for threshold determination, backed by a closed form model.
  arXiv  Detail & Related papers  (2025-01-23T17:38:22Z)
• LSTM and CNN application for core-collapse supernova search in gravitational wave real data [0.0]
  Core-collapse supernovae (CCSNe) are expected to emit gravitational wave signals that could be detected by interferometers within the Milky Way and nearby galaxies. We show potential of machine learning (ML) for multi-label classification of different CCSNe simulated signals and noise transients using real data.
  arXiv  Detail & Related papers  (2023-01-23T12:12:33Z)
• Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization [60.91600465922932]
  We present an approach that avoids the use of a dual-encoder for retrieval, relying solely on the cross-encoder. Our approach provides test-time recall-vs-computational cost trade-offs superior to the current widely-used methods.
  arXiv  Detail & Related papers  (2022-10-23T00:32:04Z)
• String-based Molecule Generation via Multi-decoder VAE [56.465033997245776]
  We investigate the problem of string-based molecular generation via variational autoencoders (VAEs) We propose a simple, yet effective idea to improve the performance of VAE for the task. In our experiments, the proposed VAE model particularly performs well for generating a sample from out-of-domain distribution.
  arXiv  Detail & Related papers  (2022-08-23T03:56:30Z)
• ESAD: End-to-end Deep Semi-supervised Anomaly Detection [85.81138474858197]
  We propose a new objective function that measures the KL-divergence between normal and anomalous data. The proposed method significantly outperforms several state-of-the-arts on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-09T08:16:35Z)
• Suppress and Balance: A Simple Gated Network for Salient Object Detection [89.88222217065858]
  We propose a simple gated network (GateNet) to solve both issues at once. With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder. In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales.
  arXiv  Detail & Related papers  (2020-07-16T02:00:53Z)

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.