PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures

• URL: http://arxiv.org/abs/2511.18116v1
• Date: Sat, 22 Nov 2025 16:41:18 GMT
• Title: PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures
• Authors: Yuheng Shao, Lizhang Wang, Changhao Li, Peixian Chen, Qinyuan Liu,
• Abstract summary: We propose a compositional approach to prompt learning for ZSAD.<n>$mathttPromptMoE$ learns a pool of expert prompts, which serve as a basis set of composable semantic primitives.<n>Our framework materializes this concept through a Visually-Guided Mixture of Prompt (VGMoP) that employs an image-gated sparse MoE to aggregate diverse normal and abnormal expert state prompts.
• Score: 8.502253878981849
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero-Shot Anomaly Detection (ZSAD) aims to identify and localize anomalous regions in images of unseen object classes. While recent methods based on vision-language models like CLIP show promise, their performance is constrained by existing prompt engineering strategies. Current approaches, whether relying on single fixed, learnable, or dense dynamic prompts, suffer from a representational bottleneck and are prone to overfitting on auxiliary data, failing to generalize to the complexity and diversity of unseen anomalies. To overcome these limitations, we propose $\mathtt{PromptMoE}$. Our core insight is that robust ZSAD requires a compositional approach to prompt learning. Instead of learning monolithic prompts, $\mathtt{PromptMoE}$ learns a pool of expert prompts, which serve as a basis set of composable semantic primitives, and a visually-guided Mixture-of-Experts (MoE) mechanism to dynamically combine them for each instance. Our framework materializes this concept through a Visually-Guided Mixture of Prompt (VGMoP) that employs an image-gated sparse MoE to aggregate diverse normal and abnormal expert state prompts, generating semantically rich textual representations with strong generalization. Extensive experiments across 15 datasets in industrial and medical domains demonstrate the effectiveness and state-of-the-art performance of $\mathtt{PromptMoE}$.

Related papers

• MUSE: Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide Image Classification [16.895269678640595]
  In computational pathology, few-shot whole slide image classification is primarily driven by the extreme scarcity of expert-labeled slides.<n>Recent vision-language methods incorporate textual semantics generated by large language models, but treat these descriptions as static class-level priors that are shared across all samples and lack sample-wise refinement.<n>We propose the MUlti-view Semantic Enhancement (MUSE), a framework that first refines semantic precision via sample-wise adaptation and then enhances semantic richness through retrieval-augmented multi-view generation.
  arXiv  Detail & Related papers  (2026-02-24T13:17:35Z)
• One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection [65.11602552904456]
  Universal visual anomaly detection (AD) aims to identify anomaly images and segment anomaly regions towards open and dynamic scenarios.<n>Current methods often struggle with complex prompt engineering, elaborate adaptation modules, and challenging training strategies.<n>This paper presents an embarrassingly simple, general, and effective framework for Universal vision Anomaly Detection (UniADet)
  arXiv  Detail & Related papers  (2026-01-09T06:05:18Z)
• Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs [61.64185573373394]
  We propose a training-free framework that uses an MLLM's intrinsic uncertainty as a proactive guidance signal.<n>We introduce a unified mechanism that scores candidate visual inputs by response uncertainty, enabling the model to autonomously focus on the most salient data.<n>Our work validates that harnessing intrinsic uncertainty is a powerful, general strategy for enhancing fine-grained multimodal performance.
  arXiv  Detail & Related papers  (2025-10-01T09:20:51Z)
• Accelerating Conditional Prompt Learning via Masked Image Modeling for Vision-Language Models [1.1925232472331495]
  Vision-language models (VLMs) like CLIP excel in zero-shot learning but often require resource-intensive training to adapt to new tasks.<n>We introduce ProMIM, a plug-and-play framework that enhances conditional prompt learning by integrating masked image modeling (MIM) into existing VLM pipelines.
  arXiv  Detail & Related papers  (2025-08-07T00:08:31Z)
• ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models [67.75439511654078]
  Large Vision-Language Models (LVLMs) have introduced a new paradigm for understanding and reasoning about image input through textual responses.<n>They face the persistent challenge of hallucination, which introduces practical weaknesses and raises concerns about their reliable deployment in real-world applications.<n>We propose ONLY, a training-free decoding approach that requires only a single query and a one-layer intervention during decoding, enabling efficient real-time deployment.
  arXiv  Detail & Related papers  (2025-07-01T16:01:08Z)
• Multimodal Prompt Alignment for Facial Expression Recognition [24.470095812039286]
  MPA-FER provides fine-grained semantic guidance to the learning process of prompted visual features.<n>Our framework outperforms state-of-the-art methods on three FER benchmark datasets.
  arXiv  Detail & Related papers  (2025-06-26T05:28:57Z)
• MemoryOut: Learning Principal Features via Multimodal Sparse Filtering Network for Semi-supervised Video Anomaly Detection [30.470777079947958]
  Video Anomaly Detection (VAD) methods based on reconstruction or prediction face two critical challenges.<n>Strong generalization capability often results in accurate reconstruction or prediction of abnormal events.<n>reliance only on low-level appearance and motion cues limits their ability to identify high-level semantic in abnormal events from complex scenes.
  arXiv  Detail & Related papers  (2025-06-03T07:14:57Z)
• Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning [125.79428219851289]
  Inst-IT is a solution to enhance LMMs in Instance understanding via explicit visual prompt Instruction Tuning.<n>Inst-IT consists of a benchmark to diagnose multimodal instance-level understanding, a large-scale instruction-tuning dataset, and a continuous instruction-tuning training paradigm.
  arXiv  Detail & Related papers  (2024-12-04T18:58:10Z)
• Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction [17.989559761931435]
  We propose a novel "Fine-grained Visual-Semantic Interaction" framework for WSI classification. It is designed to enhance the model's generalizability by leveraging the interaction between localized visual patterns and fine-grained pathological semantics. Our method demonstrates robust generalizability and strong transferability, dominantly outperforming the counterparts on the TCGA Lung Cancer dataset.
  arXiv  Detail & Related papers  (2024-02-29T16:29:53Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)
• Bayesian Prompt Learning for Image-Language Model Generalization [64.50204877434878]
  We use the regularization ability of Bayesian methods to frame prompt learning as a variational inference problem. Our approach regularizes the prompt space, reduces overfitting to the seen prompts and improves the prompt generalization on unseen prompts. We demonstrate empirically on 15 benchmarks that Bayesian prompt learning provides an appropriate coverage of the prompt space.
  arXiv  Detail & Related papers  (2022-10-05T17:05:56Z)
• Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting [77.69172089359606]
  We study multi-modal few-shot object detection (FSOD) in this paper, using both few-shot visual examples and class semantic information for detection. Our approach is motivated by the high-level conceptual similarity of (metric-based) meta-learning and prompt-based learning. We comprehensively evaluate the proposed multi-modal FSOD models on multiple few-shot object detection benchmarks, achieving promising results.
  arXiv  Detail & Related papers  (2022-04-16T16:45:06Z)

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.