Metraipolis › archive › dc_628ef3e764a5
Spatial Attention Supervision for Defect Localization: Exploiting Ground-Truth Masks as Training Signal in Diffusion-Augmented Defect Detection — arXiv:2609.06232
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06232
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:58:53.540Z
- SHA-256 of the archived text
39fdcc88f8f32e8fa3e1ddf0ce71da518c2db9227f39caf2cc6224c2336d8860- Stable URL of this page
https://metraipolis.com/documento/dc_628ef3e764a5
How to cite
Spatial Attention Supervision for Defect Localization: Exploiting Ground-Truth Masks as Training Signal in Diffusion-Augmented Defect Detection — arXiv:2609.06232 — arXiv (en), https://arxiv.org/abs/2609.06232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_628ef3e764a5 (Metraipolis archive dc_628ef3e764a5, sha256 39fdcc88f8f32e8fa3e1ddf0ce71da518c2db9227f39caf2cc6224c2336d8860)
BibTeX
@misc{dc628ef3e764a5,
title = {Spatial Attention Supervision for Defect Localization: Exploiting Ground-Truth Masks as Training Signal in Diffusion-Augmented Defect Detection — arXiv:2609.06232},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06232},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_628ef3e764a5; sha256 39fdcc88f8f32e8fa3e1ddf0ce71da518c2db9227f39caf2cc6224c2336d8860},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Ground-truth defect masks in industrial inspection datasets are typically reserved for evaluation. This paper repurposes them as spatial supervision signals during training of classification networks, teaching a model not just what to predict but where to look. The method adds an activation-based attention alignment loss that steers convolutional feature maps toward defect regions, in a mixed-supervision formulation that also accommodates samples without masks, such as diffusion-generated images. Combined with DDPM augmentation, synthetic images contribute quantity while masks contribute spatial precision. We evaluate 85 models (four CNN backbones under a 2x2 data/training factorial over five seeds, plus a Swin-V2-T transformer baseline) on the MVTec-AD bottle benchmark, with localization measured on held-out defect images excluded from classifier gradient updates. Main findings: (1) attention-guided training improves activation-based localization (Pixel-AUROC) by +18.0% for EfficientNetB0 with augmentation (p=0.005, Cohen's d=2.6) and +18.7% for ResNet50 (p=0.008), significant in four of eight CNN settings (uncorrected for multiple comparisons) with no significant change in classification; (2) for EfficientNetB0 a data x training-mode interaction is significant (p=0.002), consistent with a super-additive effect (+13.6% combined vs +1.6% summed individual effects); (3) architectures with weaker spatial representations benefit most, whereas ConvNeXt-T shows no effect, apparently because its depthwise-convolution activations yield spatially uninformative channel-mean maps; (4) unsupervised PatchCore remains the strongest localizer (Pixel-AUROC=0.983), contextualizing the supervised gains. These results show that existing evaluation masks can act as practical training signals that measurably and reproducibly improve where defect classifiers attend. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2609.06232 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T13:39:43.156Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).