Prototype-guided model improves shampoo bottle surface defect detection
Prototype-Guided Dynamic Domain Modulation and a Large-Scale Multi-SKU Benchmark for Shampoo Bottle Surface Defect Detection
Artificial Intelligence
Summary
Detecting surface defects on shampoo bottles is tricky because different bottle types look very different, even if the defect is the same. The authors created a big collection of images of many shampoo bottle types with detailed defect labels to help study this problem. They also developed a method called ProDMM that builds a visual prototype for each bottle type and uses it to better identify defects despite these differences. This approach helps the system recognize defects both across and within specific bottle types more accurately.
What this means in practice
- •For industrial quality control teams: Improve automated detection of surface defects on varied shampoo bottles using prototype-conditioned models for more accurate manufacturing inspection.
- •For manufacturing automation engineers: Integrate prototype-guided domain modulation techniques to handle appearance variation in multi-product defect detection systems for flexible production lines.
Authors
Yuehang Li, Xiao Wang, Qiang Chen, Yangyi Fan, Bo Jiang, Yaowei Wang, Jin Tang
Abstract
Industrial shampoo-bottle surface defect detection must operate across many stock keeping units (SKUs), where differences in bottle geometry, material, label layout, reflectance, and imaging conditions can substantially alter the appearance of the same defect. Existing industrial defect datasets rarely provide both instance-level defect annotations and product-variant identities, making it difficult to study SKU-aware detection under realistic manufacturing conditions. We introduce Bottle-SKU, a large-scale multi-SKU benchmark for shampoo bottle surface defect detection. Bottle-SKU contains 13,119 images, 20,419 instance-level bounding boxes, seven defect categories, and 48 bottle SKUs, enabling evaluation of both shared defect recognition and SKU-specific appearance variation. To address the challenge of SKU-specific appearance variation, we propose Prototype-Guided Dynamic Domain Modulation (ProDMM). ProDMM constructs a visual prototype for each SKU from training images and predicts a soft SKU distribution for each input. The resulting prototype-conditioned representation dynamically generates low-rank Query/Value modulation for the visual backbone and residual conditioning for defect-text-to-visual attention, while preserving the pretrained Grounding DINO detection pathway. The model is trained jointly with detection, SKU-domain classification, and modulation-regularization objectives. Experiments on Bottle-SKU and the public GC10-DET-SKU metallic surface defect dataset demonstrate the effectiveness of prototype-guided domain conditioning for industrial surface defect detection.