MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection
The CLIP model's outstanding generalization has driven recent success in Zero-Shot Anomaly Detection (ZSAD) for detecting anomalies in unseen categories. The core challenge in ZSAD is to specialize the model for anomaly detection tasks while preserving CLIP's powerful generalization capability. Existing approaches attempting to solve this challenge share the fundamental limitation of a patch-agnostic design that processes all patches monolithically without regard for their unique characteristics. To address this limitation, we propose MoECLIP, a Mixture-of-Experts (MoE) architecture for the ZSAD task, which achieves patch-level adaptation by dynamically routing each image patch to a specialized Low-Rank Adaptation (LoRA) expert based on its unique characteristics. Furthermore, to prevent functional redundancy among the LoRA experts, we introduce (1) Frozen Orthogonal Feature Separation (FOFS), which orthogonally separates the input feature space to force experts to focus on distinct information, and (2) a simplex equiangular tight frame (ETF) loss to regulate the expert outputs to form maximally equiangular representations. Comprehensive experimental results across 14 benchmark datasets spanning industrial and medical domains demonstrate that MoECLIP outperforms existing state-of-the-art methods. The code is available at https://github.com/CoCoRessa/MoECLIP.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionSimilar Papers 제목 키워드 기반
Fine-Grained Zero-Shot Learning with Attribute-Centric Representations
Recognizing unseen fine-grained categories demands a model that can distinguish subtle visual differences. This is typically achieved by transferring visual-attribute relationships from seen classes to unseen classes. Th…
Representation LearningZero-Shot LearningLearning to Route Among Specialized Experts for Zero-Shot Generalization
Recently, there has been a widespread proliferation of "expert" language models that are specialized to a specific task or domain through parameter-efficient fine-tuning. How can we recycle large collections of expert la…
parameter-efficient fine-tuningZero-shot GeneralizationEvaluating the Factuality of Zero-shot Summarizers Across Varied Domains
Recent work has shown that large language models (LLMs) are capable of generating summaries zero-shot (i.e., without explicit supervision) that, under human assessment, are often comparable or even preferred to manually …
ArticlesModular Embedding Recomposition for Incremental Learning
The advent of pre-trained Vision-Language Models (VLMs) has significantly transformed Continual Learning (CL), mainly due to their zero-shot classification abilities. Such proficiency makes VLMs well-suited for real-worl…
Incremental LearningContinual LearningZero-shot denoising via neural compression: Theoretical and algorithmic framework
Zero-shot denoising aims to denoise observations without access to training samples or clean reference images. This setting is particularly relevant in practical imaging scenarios involving specialized domains such as me…
Denoising