{
  "abstract": "Few-shot industrial surface defect detection remains challenging because annotated defect images are scarce, defect scales vary considerably, and textured backgrounds can cause false responses. This study proposes a Prototype-Aligned Multi-Scale Attention Network (PA-MSAN) that integrates multi-receptive-field feature extraction, spatial-channel attention, and region of interest (RoI)-level prototype matching within a two-stage detector. Experiments are conducted on NEU-DET under 1-shot, 3-shot, and 5-shot episode settings, with 5-shot cross-domain evaluation on GC10-DET using target-domain support prototypes. Multi-scale feature-pyramid fusion represents local textures and broader defect morphology, while attention weighting enhances defect-sensitive regions and channels before region proposal network (RPN) proposal generation and RoI Align. Few-shot classification is performed by cosine similarity between RoI features and class prototypes, and training jointly optimizes detection classification, bounding-box regression, region proposal, and Prototype Alignment Loss (PAL). Under the 5-shot NEU-DET setting, PA-MSAN achieves 92.2 ± 0.4% mean average precision (mAP)@0.5, 88.7 ± 0.4% small-object average precision (APsmall), 0.89 ± 0.01 average intersection over union (IoU), and a 4.1 ± 0.2% background false response rate, with 23.4 ms detection time and 18.7 × 10⁶ parameters. Compared with Faster R-CNN, PA-MSAN improves mAP@0.5 by 2.9 percentage points and APsmall by 3.9 percentage points while reducing the background false response rate by 1.7 percentage points. Under the 5-shot target-domain support setting, PA-MSAN achieves 86.4 ± 0.4% mAP@0.5 on GC10-DET, 5.8 percentage points (6.3%) below the corresponding NEU-DET result. The results support region-level prototype alignment for limited-label metallic surface inspection under the evaluated datasets and two-stage configuration.",
  "abstract_shown": true,
  "affiliations": [
    "School of Computer and Information Technology, Anhui Vocational and Technical College, Hefei, Anhui, China",
    "School of Electrical and Mechanical Engineering, Anhui Water Conservancy and Hydropower Vocational and Technical College, Hefei, Anhui, China"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Rubing Huang"
    },
    {
      "affs": [
        1
      ],
      "name": "Lianyi Zhao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/71as0w4k4zvg5.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0359400",
  "fulltext_url": null,
  "id": "71as0w4k4zvg5",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0359400",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2209|Industrial Vision Systems and Defect Detection"
    ],
    [
      "plos",
      "/Computer and information sciences/Digital imaging/Grayscale"
    ],
    [
      "plos",
      "/Computer and information sciences/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Engineering and technology/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Engineering and technology/Technology development/Prototypes"
    ],
    [
      "plos",
      "/Physical sciences/Materials science/Material properties/Texture"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Statistics/Similarity measures/Cosine similarity"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Statistics/Statistical noise/Gaussian noise"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Mathematical functions/Convolution"
    ],
    [
      "plos",
      "/Social sciences/Sociology/Education/Training (education)/Adaptive training"
    ]
  ],
  "openalex": "W7214626018",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0359400&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/71as0w4k4zvg5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:37Z",
      "native_id": "10.1371/journal.pone.0359400",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0359400"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "plos:materials science",
      "subfield": "materials-polymers"
    },
    {
      "field": "mathematics",
      "origin": "plos:statistics",
      "subfield": "statistics"
    }
  ],
  "title": "A prototype-aligned multi-scale attention network for few-shot industrial surface defect detection",
  "title_text": "A prototype-aligned multi-scale attention network for few-shot industrial surface defect detection",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:37Z",
  "url": "https://research.draconitic.com/paper/71as0w4k4zvg5",
  "venue": "PLOS One",
  "versions": []
}