MLMA-Net: multi-level multi-attentional learning for multi-label object detection in textile defect images

TL;DR

MLMA-Net is a novel deep learning model designed to improve multi-label textile defect detection by enhancing feature representation and attention mechanisms, especially for small and multiple defects, validated on a new dataset.

Contribution

Introduces MLMA-Net, a multi-level, multi-attentional network that enhances detection of small and multiple textile defects and provides a new dataset for evaluation.

Findings

MLMA-Net outperforms existing methods on the DHU-ML1000 dataset.

The model effectively detects small and multiple defects in textile images.

Enhanced feature representation improves defect classification accuracy.

Abstract

For the sake of recognizing and classifying textile defects, deep learning-based methods have been proposed and achieved remarkable success in single-label textile images. However, detecting multi-label defects in a textile image remains challenging due to the coexistence of multiple defects and small-size defects. To address these challenges, a multi-level, multi-attentional deep learning network (MLMA-Net) is proposed and built to 1) increase the feature representation ability to detect small-size defects; 2) generate a discriminative representation that maximizes the capability of attending the defect status, which leverages higher-resolution feature maps for multiple defects. Moreover, a multi-label object detection dataset (DHU-ML1000) in textile defect images is built to verify the performance of the proposed model. The results demonstrate that the network extracts more distinctive features and has better performance than the state-of-the-art approaches on the real-world industrial dataset.