An Incremental Knowledge Learning Framework for Continuous Defect Detection

Defect detection is one of the most essential processes for industrial quality inspection. However, in continuous defect detection (CDD), where defect categories and samples continually increase, the challenge of incremental few-shot defect detection remains unexplored. Current defect detection models fail to generalize to novel categories and suffer from catastrophic forgetting. To address these problems, this article proposes an incremental knowledge learning framework (IKLF) for CDD. The proposed framework follows the pretrain-finetuning paradigm. To realize end-to-end fine-tuning for novel categories, an incremental Region-based Convolutional Neural Network (RCNN) module is proposed to calculate cosine-similarity features of defects and decouple classwise representations. What is more, two incremental knowledge align losses are proposed to deal with catastrophic problems. The feature knowledge align (FKA) loss is designed for class-agnostic feature maps, while the logit knowledge align (LKA) loss is proposed for class-specific output logits. The combination of two align losses mitigates the catastrophic forgetting problem effectively. Experiments have been conducted on two real-world industrial inspection datasets (NEU-DET and DeepPCB). Results show that IKLF outperforms other methods on various incremental few-shot scenes, which proves the effectiveness of the proposed method.