UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting

• URL: http://arxiv.org/abs/2604.02905v1
• Date: Fri, 03 Apr 2026 09:24:34 GMT
• Title: UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting
• Abstract summary: We propose UniSpector, which shifts the focus from naive prompt-to-region matching to the principled design of a semantically structured and transferable prompt topology.<n>We introduce Inspect Anything, the first benchmark for visual-prompt-based open-set defect localization, where UniSpector significantly outperforms baselines by at least 19.7% and 15.8% in AP50b and AP50m, respectively.
• Score: 7.971808165863176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although industrial inspection systems should be capable of recognizing unprecedented defects, most existing approaches operate under a closed-set assumption, which prevents them from detecting novel anomalies. While visual prompting offers a scalable alternative for industrial inspection, existing methods often suffer from prompt embedding collapse due to high intra-class variance and subtle inter-class differences. To resolve this, we propose UniSpector, which shifts the focus from naive prompt-to-region matching to the principled design of a semantically structured and transferable prompt topology. UniSpector employs the Spatial-Spectral Prompt Encoder to extract orientation-invariant, fine-grained representations; these serve as a solid basis for the Contrastive Prompt Encoder to explicitly regularize the prompt space into a semantically organized angular manifold. Additionally, Prompt-guided Query Selection generates adaptive object queries aligned with the prompt. We introduce Inspect Anything, the first benchmark for visual-prompt-based open-set defect localization, where UniSpector significantly outperforms baselines by at least 19.7% and 15.8% in AP50b and AP50m, respectively. These results show that our method enable a scalable, retraining-free inspection paradigm for continuously evolving industrial environments, while offering critical insights into the design of generic visual prompting.

Related papers

• Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing [59.765442274924595]
  We propose a compositional visual prompt learning framework that operates entirely in the visual feature space.<n>The framework employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units.<n>Experiments on nine open-world protocols demonstrate state-of-the-art performance, strong cross-domain generalization, and robust adaptation to unseen attacks.
  arXiv  Detail & Related papers  (2026-08-18T04:18:08Z)
• Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection [59.056076147081775]
  Deepfake detection suffers from poor generalization across forgery methods.<n>Recent approaches attempt to improve generalization, but lack explicit mechanism to identify and suppress such shortcuts.<n>We propose Shortcut Subspace Suppression (S3) framework that explicitly characterizes and suppresses method-specific shortcuts.
  arXiv  Detail & Related papers  (2026-06-01T07:54:58Z)
• Beyond Open Vocabulary: Multimodal Prompting for Object Detection in Remote Sensing Images [52.7196029918473]
  Open-vocabulary object detection in remote sensing commonly relies on text-only prompting to specify target categories.<n>In practice, this assumption often breaks down in remote sensing scenarios due to task- and application-specific category semantics.<n>We propose RS-MPOD, a multimodal open-vocabulary detection framework that reformulates category specification beyond text-only prompting.
  arXiv  Detail & Related papers  (2026-02-02T11:03:01Z)
• Beyond Human-prompting: Adaptive Prompt Tuning with Semantic Alignment for Anomaly Detection [20.650740481670276]
  We propose textbfAdaptive textbfPrompt textbfTuning with semantic alignment for anomaly detection (APT)<n>APT uses self-generated anomaly samples with noise perturbations to train learnable prompts that capture context-dependent anomalies in different scenarios.<n>Our system achieves state-of-the-art performance on multiple benchmark datasets without requiring prior knowledge for prompt crafting.
  arXiv  Detail & Related papers  (2025-08-22T07:26:56Z)
• Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection [17.590853105242864]
  vision-language models (e.g. CLIP) have demonstrated remarkable performance in zero-shot anomaly detection (ZSAD)<n>Bayes-PFL is designed to learn both image-specific and image-agnostic distributions, which are jointly utilized to regularize the text prompt space and improve the model's generalization on unseen categories.<n>Experiments on 15 industrial and medical datasets demonstrate our method's superior performance.
  arXiv  Detail & Related papers  (2025-03-13T06:05:35Z)
• PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection [59.34973469354926]
  This paper proposes a one-class prompt learning method for few-shot anomaly detection, termed PromptAD. For image-level/pixel-level anomaly detection, PromptAD achieves first place in 11/12 few-shot settings on MVTec and VisA.
  arXiv  Detail & Related papers  (2024-04-08T06:53:30Z)
• Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection [57.646582245834324]
  We propose a simple yet effective deepfake detector called LSDA. It is based on a idea: representations with a wider variety of forgeries should be able to learn a more generalizable decision boundary. We show that our proposed method is surprisingly effective and transcends state-of-the-art detectors across several widely used benchmarks.
  arXiv  Detail & Related papers  (2023-11-19T09:41:10Z)
• Discrepancy-Guided Reconstruction Learning for Image Forgery Detection [10.221066530624373]
  We first propose a Discrepancy-Guided (DisGE) to extract forgery-sensitive visual patterns. We then introduce a Double-Head Reconstruction (DouHR) module to enhance genuine compact visual patterns in different granular spaces. Under DouHR, we further introduce a Discrepancy-Aggregation Detector (DisAD) to aggregate these genuine compact visual patterns.
  arXiv  Detail & Related papers  (2023-04-26T07:40:43Z)
• 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)
• 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.