FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis

• URL: http://arxiv.org/abs/2509.20295v2
• Date: Fri, 26 Sep 2025 07:41:01 GMT
• Title: FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis
• Authors: Xichen Xu, Yanshu Wang, Jinbao Wang, Xiaoning Lei, Guoyang Xie, Guannan Jiang, Zhichao Lu,
• Abstract summary: We propose a foreground-aware diffusion framework featuring two novel modules: the Anomaly-Informed Accelerated Sampling (AIAS) and the Foreground-Aware Reconstruction Module (FARM)<n>AIAS is a training-free sampling algorithm specifically designed for segmentation-oriented industrial anomaly synthesis.<n>FARM adaptively adjusts the anomaly-aware noise within the masked foreground regions at each sampling step, preserving localized anomaly signals throughout the denoising trajectory.
• Score: 30.846094090226444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial anomaly synthesis (SIAS) has emerged as a promising alternative; however, existing methods struggle to balance sampling efficiency and generation quality. Moreover, most approaches treat all spatial regions uniformly, overlooking the distinct statistical differences between anomaly and background areas. This uniform treatment hinders the synthesis of controllable, structure-specific anomalies tailored for segmentation tasks. In this paper, we propose FAST, a foreground-aware diffusion framework featuring two novel modules: the Anomaly-Informed Accelerated Sampling (AIAS) and the Foreground-Aware Reconstruction Module (FARM). AIAS is a training-free sampling algorithm specifically designed for segmentation-oriented industrial anomaly synthesis, which accelerates the reverse process through coarse-to-fine aggregation and enables the synthesis of state-of-the-art segmentation-oriented anomalies in as few as 10 steps. Meanwhile, FARM adaptively adjusts the anomaly-aware noise within the masked foreground regions at each sampling step, preserving localized anomaly signals throughout the denoising trajectory. Extensive experiments on multiple industrial benchmarks demonstrate that FAST consistently outperforms existing anomaly synthesis methods in downstream segmentation tasks. We release the code at: https://github.com/Chhro123/fast-foreground-aware-anomaly-synthesis.

Related papers

• Improving Anomaly Detection with Foundation-Model Synthesis and Wavelet-Domain Attention [54.73850941855912]
  anomaly synthesis pipeline (FMAS) generates highly realistic anomalous samples without fine-tuning or class-specific training.<n>Wavelet Domain Attention Module (WDAM) exploits adaptive sub-band processing to enhance anomaly feature extraction.
  arXiv  Detail & Related papers  (2026-03-03T13:17:08Z)
• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection [52.5174167737992]
  Video anomaly detection (VAD) aims to identify abnormal events in videos.<n>We propose SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations.<n>Our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data.
  arXiv  Detail & Related papers  (2026-02-27T13:48:50Z)
• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rays [10.059919773758562]
  Unsupervised anomaly detection aims to identify anomalies without pixel-level annotations.<n>This paper presents a novel Anatomy-aware Realistic Texture-based Anomaly Synthesis framework (ART-ASyn) for chest X-rays.<n>ART-ASyn generates realistic and anatomically consistent lung opacity related anomalies using texture-based augmentation.
  arXiv  Detail & Related papers  (2025-11-29T04:06:58Z)
• STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment [29.572404530614175]
  Industrial Anomaly Synthesis (SIAS) plays a pivotal role in enhancing the performance of downstream anomaly segmentation.<n>SIAS methods face several critical limitations.<n>We propose Graded diffusion with Explicit mask alignment, termed STAGE.
  arXiv  Detail & Related papers  (2025-09-08T13:47:01Z)
• SARD: Segmentation-Aware Anomaly Synthesis via Region-Constrained Diffusion with Discriminative Mask Guidance [4.65786322515141]
  We propose SARD (Segmentation-Aware anomaly synthesis via Region-constrained Diffusion with discriminative mask Guidance), a novel diffusion-based framework specifically designed for anomaly generation.<n>SARD surpasses existing methods in segmentation accuracy and visual quality, setting a new state-of-the-art for pixel-level anomaly synthesis.
  arXiv  Detail & Related papers  (2025-08-05T06:43:01Z)
• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection [2.3494824114381814]
  Anomaly detection plays a vital role in the inspection of industrial images.<n>Most existing methods require separate models for each category, resulting in multiplied deployment costs.<n>We propose a novel Center-aware Residual Anomaly Synthesis (CRAS) method for multi-class anomaly detection.
  arXiv  Detail & Related papers  (2025-05-23T06:56:44Z)
• Open-set Anomaly Segmentation in Complex Scenarios [88.11076112792992]
  This paper introduces ComsAmy, a benchmark for open-set anomaly segmentation in complex scenarios.<n>ComsAmy encompasses a wide spectrum of adverse weather conditions, dynamic driving environments, and diverse anomaly types.<n>We propose a novel energy-entropy learning (EEL) strategy that integrates the complementary information from energy and entropy.
  arXiv  Detail & Related papers  (2025-04-28T12:00:10Z)
• Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection [1.5680795779726031]
  Unsupervised anomaly detection methods can identify surface defects in industrial images by leveraging only normal samples for training.<n>We propose a novel Progressive Boundary-guided Anomaly Synthesis (PBAS) strategy, which can directionally synthesize crucial feature-level anomalies without auxiliary textures.<n>Our method achieves state-of-the-art performance and the fastest detection speed on three widely used industrial datasets.
  arXiv  Detail & Related papers  (2024-12-23T10:26:26Z)
• 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)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)

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.