Visual Quality Score Assessment of Large White Goods in Remanufacture with Multi-View Deformable-DETR
The paper presents a multi-view framework for automated quality scoring of large white goods using a deformable DETR model.
The paper presents a novel multi-view framework for quality scoring that aggregates information across redundant views to extract fine-grained features.
Before reading this…
Applications
- →Remanufacturing
- →Quality control
To understand this paper, make sure you know these concepts first:
- Computer visionfind papers →
- Deep learningfind papers →
Abstract
More Like ThisRemanufacturing large white goods is essential for a circular economy, yet visual quality assessment remains a manual bottleneck for training and pricing. Conventional detection methods require extensive annotation and struggle with small defects in high-resolution multi-view data. We present a multi-view framework based on Deformable-DETR for automated quality scoring that aggregates information across redundant views to extract fine-grained features. To enhance robustness with limited labels, we employ self-supervised pretraining followed by supervised fine-tuning on expert-annotated scores. Additionally, a linear projection over frozen feature maps identifies regions of interest to explain model decisions. Evaluated on an industrial multi-view dataset, our approach delivers precise quality assessments while reducing reliance on manual annotation and per-part customization, enabling scalable and transparent inspection for remanufacturing lines.