2026-10-14T20:21:23Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34016222 2026-09-28T17:30:05Z category_146 category_7 category_12 category_13 category_15 category_734 category_931 category_132 portal_5 item_type_3 month_year_09_2026

<p>Data augmentation parameter settings.</p> Rubing Huang (20042874) Lianyi Zhao (22495717) Space Science Medicine Cell Biology Genetics Neuroscience Biological Sciences not elsewhere classified Information Systems not elsewhere classified Infectious Diseases object average precision mean average precision cause false responses broader defect morphology annotated defect images 9 percentage points 8 percentage points 7 percentage points 10 &# 8310 01 average intersection msan achieves 92 msan achieves 86 field feature extraction scale attention network results support region domain support setting domain support prototypes prototype alignment loss level prototype alignment shot episode settings msan improves map region proposal network det using target map )@ 0 apsmall ), 0 scale feature domain evaluation channel attention region proposal iou ), class prototypes shot target proposal generation det setting xlink "> textured backgrounds study proposes stage detector sensitive regions roi features roi align pal ). faster r evaluated datasets cosine similarity box regression <div><p>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.</p></div> 2026-09-28T17:29:43Z Dataset Dataset 10.1371/journal.pone.0359400.t002 https://figshare.com/articles/dataset/_p_Data_augmentation_parameter_settings_p_/34016222 CC BY 4.0