Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme

• URL: http://arxiv.org/abs/2406.18197v4
• Date: Wed, 11 Sep 2024 01:26:34 GMT
• Title: Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme
• Authors: Pi-Wei Chen, Jerry Chun-Wei Lin, Jia Ji, Feng-Hao Yeh, Zih-Ching Chen, Chao-Chun Chen,
• Abstract summary: Pre-trained vision-language models (VLMs) are highly adaptable to various downstream tasks through few-shot learning. Traditional methods depend on human-crafted prompts that require prior knowledge of specific anomaly types. Our goal is to develop a human-free prompt-based anomaly detection framework that optimally learns prompts through data-driven methods.
• Score: 19.732769780675977
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pre-trained vision-language models (VLMs) are highly adaptable to various downstream tasks through few-shot learning, making prompt-based anomaly detection a promising approach. Traditional methods depend on human-crafted prompts that require prior knowledge of specific anomaly types. Our goal is to develop a human-free prompt-based anomaly detection framework that optimally learns prompts through data-driven methods, eliminating the need for human intervention. The primary challenge in this approach is the lack of anomalous samples during the training phase. Additionally, the Vision Transformer (ViT)-based image encoder in VLMs is not ideal for pixel-wise anomaly segmentation due to a locality feature mismatch between the original image and the output feature map. To tackle the first challenge, we have developed the Object-Attention Anomaly Generation Module (OAGM) to synthesize anomaly samples for training. Furthermore, our Meta-Guiding Prompt-Tuning Scheme (MPTS) iteratively adjusts the gradient-based optimization direction of learnable prompts to avoid overfitting to the synthesized anomalies. For the second challenge, we propose Locality-Aware Attention, which ensures that each local patch feature attends only to nearby patch features, preserving the locality features corresponding to their original locations. This framework allows for the optimal prompt embeddings by searching in the continuous latent space via backpropagation, free from human semantic constraints. Additionally, the modified locality-aware attention improves the precision of pixel-wise anomaly segmentation.

Related papers

• Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection [88.34095233600719]
  FAPrompt is a novel framework designed to learn Fine-grained Abnormality Prompts for more accurate ZSAD. It substantially outperforms state-of-the-art methods by at least 3%-5% AUC/AP in both image- and pixel-level ZSAD tasks.
  arXiv  Detail & Related papers  (2024-10-14T08:41:31Z)
• Vision-Language Models Assisted Unsupervised Video Anomaly Detection [3.1095294567873606]
  Anomaly samples present significant challenges for unsupervised learning methods. Our method employs a cross-modal pre-trained model that leverages the inferential capabilities of large language models. By mapping high-dimensional visual features to low-dimensional semantic ones, our method significantly enhance the interpretability of unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2024-09-21T11:48:54Z)
• AnoPLe: Few-Shot Anomaly Detection via Bi-directional Prompt Learning with Only Normal Samples [6.260747047974035]
  AnoPLe is a multi-modal prompt learning method designed for anomaly detection without prior knowledge of anomalies. The experimental results demonstrate that AnoPLe achieves strong FAD performance, recording 94.1% and 86.2% Image AUROC on MVTec-AD and VisA respectively.
  arXiv  Detail & Related papers  (2024-08-24T08:41:19Z)
• Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts [57.01985221057047]
  This paper introduces a novel method that learnstemporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs) Our method achieves state-of-theart performance on three public benchmarks for the WSVADL task.
  arXiv  Detail & Related papers  (2024-08-12T03:31:29Z)
• Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models [7.350203999073509]
  Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training models to subtle yet intentionally designed perturbations in images and texts. To the best of our knowledge, it is the first work through multimodal decision boundaries to explore the creation of a universal, sample-agnostic perturbation that applies to any image.
  arXiv  Detail & Related papers  (2024-08-06T06:25:39Z)
• GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [68.14842693208465]
  GeneralAD is an anomaly detection framework designed to operate in semantic, near-distribution, and industrial settings. We propose a novel self-supervised anomaly generation module that employs straightforward operations like noise addition and shuffling to patch features. We extensively evaluated our approach on ten datasets, achieving state-of-the-art results in six and on-par performance in the remaining.
  arXiv  Detail & Related papers  (2024-07-17T09:27:41Z)
• Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection [18.414762007525137]
  Large vision-language models (LVLMs) are proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges. We present ALFA, a training-free approach designed to address these challenges via a unified model.
  arXiv  Detail & Related papers  (2024-04-15T10:42:22Z)
• Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
  We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets. We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
  arXiv  Detail & Related papers  (2024-01-06T07:30:41Z)
• Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation [49.827306773992376]
  Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions. Our proposed method attains state-of-the-art performance in both classification and segmentation CTTA tasks.
  arXiv  Detail & Related papers  (2023-12-19T15:34:52Z)
• LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection [12.596635603629725]
  We develop a unified model to detect anomalies from objects belonging to multiple classes when only normal data is accessible. We first explore the generative-based approach and investigate latent diffusion models for reconstruction. We introduce a feature editing strategy that modifies the input feature space of the diffusion model to further alleviate identity shortcuts''
  arXiv  Detail & Related papers  (2023-07-16T14:41:22Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)

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.