Multi-Path Attention Fusion Transformer for Spectral Learning in Corn Quality Assessment

TL;DR

This paper introduces SpecTran, a new Transformer model that improves the prediction of corn quality traits using near-infrared spectra.

Contribution

The novel contribution is SpecTran, a spectral Transformer with adaptive multi-scale patch embedding and hierarchical fusion for corn quality assessment.

Findings

SpecTran achieved an average R2 score of 0.483 for predicting corn traits like moisture, starch, oil, and protein.

It reduced RMSE by 11.2% for protein and 10.7% for oil compared to the best baseline model.

The model effectively captures multi-scale spectral patterns and provides interpretable insights.

Abstract

Accurately modeling the nonlinear relationships between near-infrared (NIR) spectral signatures and biochemical traits in corn remains a major challenge. A key difficulty lies in capturing multi-scale contextual dependencies—ranging from local absorption peaks to global spectral patterns—that jointly determine quality constituents such as protein and oil. To address this, we propose SpecTran, a spectral Transformer network specifically designed for NIR regression. SpecTran integrates three key components: adaptive multi-scale patch embedding which extracts spectral features at multiple resolutions to capture both fine and coarse patterns, spectral-enhanced positional encoding which preserves wavelength order information more effectively than standard encoding, and hierarchical feature fusion for robust multi-task prediction. Evaluated on the public Eigenvector corn dataset, SpecTran had a performance across four key traits—moisture, starch, oil, and protein—with an average R2 of 0.483. It reduced the RMSE by 11.2% for protein and 10.7% for oil compared to the best-performing baseline, which is the standard Transformer model. These results demonstrate SpecTran’s superior ability to model complex spectral dynamics while providing interpretable insights, offering a reliable framework for NIR-based agricultural quality assessment.

Figures