Lightweight spatial-channel feature disentanglement modeling with confidence evaluation for uncertain industrial image

Process uncertainty has a significant impact on industrial image processing. Existing deep learning methods were established on high-quality datasets without considering the uncertainty. This paper proposes lightweight spatial-channel feature disentanglement modeling with confidence evaluation for uncertain industrial images. First, spatial-channel feature disentanglement modeling inspired by tensor decomposition aims to balance the computational efficiency and feature expression capabilities. Second, collaborative learning with confidence evaluation is designed to cope with uncertain samples. Then, representative features are fine-tuned on high-confidence datasets for optimal performance. Complexity analysis and experiments verified the effectiveness, computational efficiency, and robustness of the proposed model. © 2024 Elsevier Inc.