A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2510.13093v1
• Date: Wed, 15 Oct 2025 02:26:35 GMT
• Title: A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection
• Authors: Ningkang Peng, Yuzhe Mao, Yuhao Zhang, Linjin Qian, Qianfeng Yu, Yanhui Gu, Yi Chen, Li Kong,
• Abstract summary: We formalize the core task as quantifying the Semantic Surprise of a new sample.<n>We then introduce the Semantic Surprise Vector (SSV), a universal probe that decomposes a sample's total surprise into three complementary dimensions: conformity, novelty, and ambiguity.<n> Experiments demonstrate that our framework not only establishes a new state-of-the-art (sota) on the challenging ternary task, but its robust representations also achieve top results on conventional binary benchmarks.
• Score: 9.10958906714455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Out-of-Distribution (OOD) detection is a cornerstone for the safe deployment of AI systems in the open world. However, existing methods treat OOD detection as a binary classification problem, a cognitive flattening that fails to distinguish between semantically close (Near-OOD) and distant (Far-OOD) unknown risks. This limitation poses a significant safety bottleneck in applications requiring fine-grained risk stratification. To address this, we propose a paradigm shift from a conventional probabilistic view to a principled information-theoretic framework. We formalize the core task as quantifying the Semantic Surprise of a new sample and introduce a novel ternary classification challenge: In-Distribution (ID) vs. Near-OOD vs. Far-OOD. The theoretical foundation of our work is the concept of Low-Entropy Semantic Manifolds, which are explicitly structured to reflect the data's intrinsic semantic hierarchy. To construct these manifolds, we design a Hierarchical Prototypical Network. We then introduce the Semantic Surprise Vector (SSV), a universal probe that decomposes a sample's total surprise into three complementary and interpretable dimensions: conformity, novelty, and ambiguity. To evaluate performance on this new task, we propose the Normalized Semantic Risk (nSR), a cost-sensitive metric. Experiments demonstrate that our framework not only establishes a new state-of-the-art (sota) on the challenging ternary task, but its robust representations also achieve top results on conventional binary benchmarks, reducing the False Positive Rate by over 60% on datasets like LSUN.

Related papers

• The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation [11.984098021215878]
  We introduce the Semantic-Preserving Adrial Code Injection (SPACI) Framework and the Abstract Syntax Tree-Aware Semantic Injection Protocol (AST-ASIP)<n>These methods exploit the Syntax-Semantics Gap by embedding adversarial directives into syntactically inert regions (trivia nodes) of the Abstract Syntax Tree.<n>Through a large-scale evaluation of 9 SOTA models across 25,000 submissions in Python, C, C++, and Java, we reveal catastrophic failure rates (>95%) in high-capacity open-weights models like DeepSeek-V3.
  arXiv  Detail & Related papers  (2026-01-29T07:40:58Z)
• SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classification [3.189189590825304]
  SeNeDiF-OOD is a novel methodology based on Semantic Nested Dichotomy Fusion.<n>We present a case study using MonuMAI, a real-world architectural style recognition system exposed to an open environment.
  arXiv  Detail & Related papers  (2026-01-26T18:01:46Z)
• Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation [17.405818788700234]
  We present a Collaborative Multi-Agent Reasoning Framework that explicitly decouples Semantic Planning from Visual Synthesis.<n>Our method generates a structured, explicit plan before pixel generation, enabling visually and semantically coherent single-pass synthesis.<n>Addressing the limitations of traditional metrics in assessing inferred invisible content, we introduce the MAC-Score, a novel human-aligned evaluation metric.
  arXiv  Detail & Related papers  (2025-12-24T04:39:45Z)
• Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment? [73.80382983108997]
  Representation intervention aims to locate and modify the representations that encode the underlying concepts in Large Language Models.<n>If the interventions are faithful, the intervened LLMs should erase the harmful concepts and be robust to both in-distribution adversarial prompts and the out-of-distribution jailbreaks.<n>We propose Concept Concentration (COCA), which simplifies the decision boundary between harmful and benign representations.
  arXiv  Detail & Related papers  (2025-05-24T12:23:52Z)
• A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection [13.109309606764754]
  We introduce a plug-in detection framework that leverages internal layer-wise inconsistencies within the target model itself.<n>Our method achieves state-of-the-art detection performance with negligible computational overhead.
  arXiv  Detail & Related papers  (2025-05-19T00:48:53Z)
• Advancing Neural Network Verification through Hierarchical Safety Abstract Interpretation [52.626086874715284]
  We introduce a novel problem formulation called Abstract DNN-Verification, which verifies a hierarchical structure of unsafe outputs.<n>By leveraging abstract interpretation and reasoning about output reachable sets, our approach enables assessing multiple safety levels during the formal verification process.<n>Our contributions include a theoretical exploration of the relationship between our novel abstract safety formulation and existing approaches.
  arXiv  Detail & Related papers  (2025-05-08T13:29:46Z)
• The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection [75.65876949930258]
  Out-of-distribution (OOD) detection is essential for model trustworthiness. We show that the superior OOD detection performance of state-of-the-art methods is achieved by secretly sacrificing the OOD generalization ability.
  arXiv  Detail & Related papers  (2024-10-12T07:02:04Z)
• NLP Verification: Towards a General Methodology for Certifying Robustness [9.897538432223714]
  Machine Learning (ML) has exhibited substantial success in the field of Natural Language Processing (NLP)<n>As these systems are increasingly integrated into real-world applications, ensuring their safety and reliability becomes a primary concern.<n>We propose a general methodology to analyse the effect of the embedding gap, a problem that refers to the discrepancy between verification of geometric subspaces and the semantic meaning of sentences.
  arXiv  Detail & Related papers  (2024-03-15T09:43:52Z)
• Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval [139.21955930418815]
  Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. We propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
  arXiv  Detail & Related papers  (2023-09-29T09:41:19Z)
• STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection [80.04000067312428]
  We propose a Self-adapTive Ambiguity Reduction (STAR) loss by exploiting the properties of semantic ambiguity. We find that semantic ambiguity results in the anisotropic predicted distribution, which inspires us to use predicted distribution to represent semantic ambiguity. We also propose two kinds of eigenvalue restriction methods that could avoid both distribution's abnormal change and the model's premature convergence.
  arXiv  Detail & Related papers  (2023-06-05T10:33:25Z)
• Full-Spectrum Out-of-Distribution Detection [42.98617540431124]
  We take into account both shift types and introduce full-spectrum OOD (FS-OOD) detection. We propose SEM, a simple feature-based semantics score function. SEM significantly outperforms current state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-11T17:59:14Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)
• FAR: A General Framework for Attributional Robustness [42.49606659285249]
  We define a novel framework for attributional robustness (FAR) for training models with robust attributions. We show that FAR is a generalized, less constrained formulation of currently existing training methods. We then propose two new instantiations of this framework, AAT and AdvAAT, that directly optimize for both robust attributions and predictions.
  arXiv  Detail & Related papers  (2020-10-14T20:33:00Z)

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.