A Novel Two-Way Transfer Learning Approach for Enhanced Fabric Fault Detection

Fabric defect detection is a crucial task in the textile industry, where early identification of faults ensures product qualityand minimizes production losses. Conventional inspection methods, often manual and subjective, are insufficient for realtime and large-scale textile monitoring. While deep learning has significantly advanced defect detection performance, itseffectiveness is hindered by the scarcity of labeled textile datasets and the domain gap between generic image features andfabric-specific textures. To overcome these limitations, this paper proposes a Two-Way Transfer Learning (TWTL)Approachfor fabric fault detection, which leverages bidirectional knowledge transfer between a source domain (e.g., ImageNet) and atarget domain (TILDA datasets). Our method integrates both forward and backward transfer mechanisms to enhancefeature adaptability and defect classification accuracy. Experimental results on benchmark datasets such as TILDAdemonstrate that the proposed approach outperforms traditional CNNs and one-way transfer learning models with notableimprovements in performance metrics such as accuracy, precision etc. The optimized lightweight architecture of the modelfacilitates low-latency inference on edge devices, ensuring its applicability for real-time automated textile inspection inresource-constrained environments.