Search papers, labs, and topics across Lattice.
This paper presents FedTR, a federated learning framework that integrates transfer learning to enhance industrial visual inspection tasks, particularly in identifying label defects through end-to-end text recognition. By initially training on a publicly available dataset and subsequently fine-tuning on limited private data, FedTR addresses the challenges posed by data scarcity and complex inspection requirements. The framework achieves impressive word-level accuracy rates of 95.5% and 94.2% on homogeneous and heterogeneous datasets, respectively, matching the performance of centralized training approaches.
FedTR achieves 95.5% accuracy in label defect identification, rivaling centralized models while preserving data privacy in federated learning settings.
Federated learning (FL) is a collaborative learning scheme to train deep learning models, where collaborating parties can consolidate their models without sharing local data with other parties, hence preserving data privacy. Nevertheless, when implementing FL in Industrial visual inspection (IVI), the constraints posed by limited data availability and the intricate nature of the inspection tasks significantly impact the performance of the resulting model. This paper introduces FedTR, a novel FL framework incorporating transfer learning designed for Autonomous IVI, focusing on the challenging task of identifying label defects through end-to-end text recognition. Transfer learning is a method that leverages the knowledge of a pre-trained model to adapt to a different dataset. FedTR initially trains the model using a publicly available dataset, after which performs the essential federated learning process with model fine-tuning on the distributed and limited private data. Extensive experiment results demonstrate the effectiveness and feasibility of FedTR on private ink cartridge datasets for label defect identification. FedTR achieves an end-to-end text recognition word-level accuracy of 95.5% and 94.2% on homogeneous and heterogeneous data respectively. Additionally, it attains performance levels that are on par with those achieved through centralized training.
