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

• URL: http://arxiv.org/abs/2512.06845v1
• Date: Sun, 07 Dec 2025 13:43:19 GMT
• Title: Pseudo Anomalies Are All You Need: Diffusion-Based Generation for Weakly-Supervised Video Anomaly Detection
• Abstract summary: We introduce PA-VAD, a generation-driven approach that learns a detector from synthesized pseudo-abnormal videos paired with real normal videos.<n>For synthesis, we select class-relevant initial images with CLIP and refine prompts with a vision-language model to improve fidelity and scene consistency.<n>For training, we mitigate excessive video magnitude in synthesized anomalies by an domain-aligned regularized module.
• Score: 2.4832691511446163
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• GV-VAD : Exploring Video Generation for Weakly-Supervised Video Anomaly Detection [6.09434007746295]
  Video anomaly detection (VAD) plays a critical role in public safety applications such as intelligent surveillance.<n>We propose a generative video-enhanced weakly-supervised VAD framework to produce semantically controllable and physically plausible synthetic videos.<n>The proposed framework outperforms state-of-the-art methods on UCF-Crime datasets.
  arXiv  Detail & Related papers  (2025-08-01T04:42:40Z)
• Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal [53.15046196592023]
  We introduce test-time adaptation into adverse weather removal in videos. We propose the first framework that integrates test-time adaptation into the iterative diffusion reverse process.
  arXiv  Detail & Related papers  (2024-03-12T14:21:30Z)
• Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection [16.77262005540559]
  A novel framework is proposed to guide the learning of suspected anomalies from event prompts. It enables a new multi-prompt learning process to constrain the visual-semantic features across all videos. Our proposed model outperforms most state-of-the-art methods in terms of AP or AUC.
  arXiv  Detail & Related papers  (2024-03-02T10:42:47Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• Delving into CLIP latent space for Video Anomaly Recognition [24.37974279994544]
  We introduce the novel method AnomalyCLIP, the first to combine Large Language and Vision (LLV) models, such as CLIP. Our approach specifically involves manipulating the latent CLIP feature space to identify the normal event subspace. When anomalous frames are projected onto these directions, they exhibit a large feature magnitude if they belong to a particular class.
  arXiv  Detail & Related papers  (2023-10-04T14:01:55Z)
• Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors [117.61449210940955]
  We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. We introduce an approach to weight tokens based on motion gradients, thus shifting the focus from the static background scene to the foreground objects. We generate synthetic abnormal events to augment the training videos, and task the masked AE model to jointly reconstruct the original frames.
  arXiv  Detail & Related papers  (2023-06-21T06:18:05Z)
• Multi-Contextual Predictions with Vision Transformer for Video Anomaly Detection [22.098399083491937]
  understanding of thetemporal context of a video plays a vital role in anomaly detection. We design a transformer model with three different contextual prediction streams: masked, whole and partial. By learning to predict the missing frames of consecutive normal frames, our model can effectively learn various normality patterns in the video.
  arXiv  Detail & Related papers  (2022-06-17T05:54:31Z)
• UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection [103.06327681038304]
  We propose a supervised open-set benchmark composed of multiple virtual scenes for video anomaly detection. Unlike existing data sets, we introduce abnormal events annotated at the pixel level at training time. We show that UBnormal can enhance the performance of a state-of-the-art anomaly detection framework.
  arXiv  Detail & Related papers  (2021-11-16T17:28:46Z)
• Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning [25.787860059872106]
  Anomaly detection in surveillance videos is a challenging task due to the diversity of anomalous video content and duration. We propose an anomaly detection framework, called Anomaly Regression Net (AR-Net), which only requires video-level labels in training stage. Our method yields a new state-of-the-art result for video anomaly detection on ShanghaiTech dataset.
  arXiv  Detail & Related papers  (2021-04-15T06:41:23Z)
• Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction [61.17654438176999]
  We propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design. Our proposed method obtains the frame-level AUROC score of 88.3% on the CUHK Avenue dataset.
  arXiv  Detail & Related papers  (2020-11-05T11:34:12Z)
• Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection [114.9714355807607]
  We show that applying self-trained deep ordinal regression to video anomaly detection overcomes two key limitations of existing methods. We devise an end-to-end trainable video anomaly detection approach that enables joint representation learning and anomaly scoring without manually labeled normal/abnormal data.
  arXiv  Detail & Related papers  (2020-03-15T08:44:55Z)

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.