UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915912730279936 |
|---|---|
| author | Kim, Geonuk Kim, Minhoi Lee, Kangil Kim, Minsu Jeon, Hyeonseong Han, Jeonghoon Lim, Hyoungjoon Yim, Junho |
| author_facet | Kim, Geonuk Kim, Minhoi Lee, Kangil Kim, Minsu Jeon, Hyeonseong Han, Jeonghoon Lim, Hyoungjoon Yim, Junho |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02905 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting Kim, Geonuk Kim, Minhoi Lee, Kangil Kim, Minsu Jeon, Hyeonseong Han, Jeonghoon Lim, Hyoungjoon Yim, Junho Computer Vision and Pattern Recognition 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. |
| title | UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.02905 |