Research
Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models
arXiv:2604.07802v1 Announce Type: new Abstract: Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) pe
arXiv:2604.07802v1 Announce Type: new Abstract: Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) performance remain poorly understood. Current methods predominantly treat VLMs as black-box feature extractors, assuming that anomaly-specific knowledge must be acquired through external adapters or memory banks. In this paper, we challenge this assumption by arguing that anomaly knowledge is intrinsically embedded within pre-trained models but remains latent and under-activated. We hypothesize that this knowledge is concentrated within a sparse subset of anomaly-sensitive neurons. To validate this, we propose latent anomaly knowledge excavation (LAKE), a training-free framework that identifies and elicits these critical neuronal signals using only a minimal set of normal samples. By isolating these sensitive neurons, LAKE constructs a highly compact normality representation that integrates visual structural deviations with cross-modal semantic activations. Extensive experiments on industrial AD benchmarks demonstrate that LAKE achieves state-of-the-art performance while providing intrinsic, neuron-level interpretability. Ultimately, our work advocates for a paradigm shift: redefining anomaly detection as the targeted activation of latent pre-trained knowledge rather than the acquisition of a downstream task.
Related
- Mitigating Entangled Steering in Large Vision-Language Models for Hallucination Reduction
- Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding
- Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
- GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis
- Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data
Source: arXiv cs.CV | 2026-04-10