Research indexJournal article
Collaborative Filter Pruning for Efficient Automatic Surface Defect Detection
Wang, Fan, Ling and 3 others
IEEE Transactions on Industrial Informatics23 Jun 2023
NobleIDark:/48914/w1/20260524/7F30CF3DDOI10.1109/tii.2023.3288208
Collaborative Filter Pruning for Efficient Automatic Surface Defect Detection
Wang, Fan, Ling and 3 others · IEEE Transactions on Industrial Informatics · 2023 · Subscription
NobleIDark:/48914/w1/20260524/7F30CF3DDOI10.1109/tii.2023.3288208
The full text is at the publisher
You can read the abstract here, or open it at the publisher.
Abstract
Surface defect detection is a critical task in industrial production, and numerous methods have been proposed to achieve high detection accuracy. Although deep-learning-based approaches have achieved state-of-the-art (SOTA) performances, their vast computational cost and high memory footprint prevent their deployment in resource-constrained environments. To address this problem, we propose a collaborative filter pruning method for the defect detection model, which significantly reduces the number of required calculations and parameters while maintaining high performance, even in cases with tasks suffering from the class imbalance problem. Our method aims to obtain lightweight pruned models by removing unimportant filters according to their importance evaluated by both structural similarity and detail richness of corresponding feature maps. Moreover, to improve the performance of pruned models, we propose a knowledge-fused fine-tuning approach that fuses the knowledge derived from two teacher networks to look after both representation learning and classifier learning, alleviating the class imbalance problem. Experimental results on four public datasets demonstrate that the proposed approach performs favorably relative to the SOTA methods. In particular, the proposed method achieves 39× and 59× parameter compression for VGG-16 and ResNet-50, respectively, on the NEU-CLS dataset, with a very small detection accuracy loss (<0.2%).