Paper Reading AI Learner

Pseudo Anomalies Are All You Need: Diffusion-Based Generation for Weakly-Supervised Video Anomaly Detection

2025-12-07 13:43:19
Satoshi Hashimoto, Hitoshi Nishimura, Yanan Wang, Mori Kurokawa

Abstract

Deploying video anomaly detection in practice is hampered by the scarcity and collection cost of real abnormal footage. We address this by training without any real abnormal videos while evaluating under the standard weakly supervised split, and we introduce PA-VAD, a generation-driven approach that learns a detector from synthesized pseudo-abnormal videos paired with real normal videos, using only a small set of real normal images to drive synthesis. For synthesis, we select class-relevant initial images with CLIP and refine textual prompts with a vision-language model to improve fidelity and scene consistency before invoking a video diffusion model. For training, we mitigate excessive spatiotemporal magnitude in synthesized anomalies by an domain-aligned regularized module that combines domain alignment and memory usage-aware updates. Extensive experiments show that our approach reaches 98.2% on ShanghaiTech and 82.5% on UCF-Crime, surpassing the strongest real-abnormal method on ShanghaiTech by +0.6% and outperforming the UVAD state-of-the-art on UCF-Crime by +1.9%. The results demonstrate that high-accuracy anomaly detection can be obtained without collecting real anomalies, providing a practical path toward scalable deployment.

Abstract (translated)

在实践中部署视频异常检测时,由于真实异常视频的稀缺性和收集成本问题而面临挑战。为了解决这个问题,我们提出了一种方法,在训练时不使用任何真实的异常视频,并且评估是在标准弱监督数据集划分下进行的。为此,我们引入了PA-VAD(Pseudo-Anomaly Video Anomaly Detection),这是一种生成驱动的方法,通过从合成的伪异常视频和真实正常视频对中学习检测器来工作。此方法仅需使用少量的真实正常图像作为驱动力来进行合成。 在生成阶段,我们首先利用CLIP选择与特定类别相关的初始图像,并且使用视觉-语言模型优化文本提示以提高生成内容的保真度和场景一致性,在此基础上调用视频扩散模型进行具体生成过程。 为了训练我们的模型并减少合成异常中过度的空间时间量级问题,我们在PA-VAD中引入了一个结合领域对齐和内存感知更新策略的模块。这个域对准正则化模块旨在减轻由于数据不足而产生的不自然或过度放大的异常效果。 经过广泛的实验验证,在上海科技大学的数据集上我们的方法达到了98.2%的准确率,并在UCF-Crime数据集中实现了82.5%,分别比最强的真实异常方法在上海科技大学的数据集上的性能高出0.6%,以及在UCF-Crime数据集上的UVAD最新成果高出了1.9%。 这些结果表明,通过不依赖于收集真实的异常视频样本,仍可以实现高准确率的异常检测。这为大规模部署提供了一条切实可行的道路。

URL

https://arxiv.org/abs/2512.06845

PDF

https://arxiv.org/pdf/2512.06845.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot