# Convolutional Neural Networks in Vis-NIR Chemometrics: From Contradiction to Conditional Design

arXiv: https://arxiv.org/abs/2605.02636 · HTML: https://mlsanity.com/paper/2605.02636/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 114 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics](https://mlsanity.com/paper/1710.01927/) (2017)
- [Explainable Predictive Modeling for Limited Spectral Data](https://mlsanity.com/paper/2202.04527/) (2022)
- [Automatic Neural Network Hyperparameter Optimization for Extrapolation: Lessons Learned from Visible and Near-Infrared Spectroscopy of Mango Fruit](https://mlsanity.com/paper/2210.01124/) (2022)
- [SHAPCA: Consistent and Interpretable Explanations for Machine Learning Models on Spectroscopy Data](https://mlsanity.com/paper/2603.19141/) (2026)

## Built on by (most cited first, 1 of 1)

- [Using Data-Derived Priors to Guide CNN Architecture Design for NIR Chemometrics](https://mlsanity.com/paper/2607.25636/) (2026)

## Abstract (arXiv)

Near-infrared (NIR and Vis-NIR) spectroscopy is widely used for rapid, non-destructive analysis in food, agriculture, pharmaceuticals, process analytical technology, and bioprocess monitoring. Nevertheless, deep-learning studies in NIR chemometrics often reach conflicting conclusions about convolutional neural network (CNN) design, including kernel size, depth, preprocessing, model complexity, and transfer robustness. This review argues that many apparent contradictions reflect incomplete experimental conditioning rather than incompatible findings. CNN performance depends on interactions among spectral physics, dataset regime, acquisition protocol, validation design, and deployment conditions. We organize the literature around three moderators. First, NIR signals are indirect, highly collinear, and shaped by broad overlapping bands, scattering, temperature, and matrix effects. Second, CNN design should be interpreted through receptive-field reasoning: kernel size, depth, dilation, and multi-scale branches determine the wavelength span available to the model, whereas the effective receptive field indicates which parts are actually used. Third, validation design can behave as a hidden hyperparameter because random splits may reward architectures that exploit shared batch, instrument, season, or process-run structure instead of transferable chemical information. We therefore propose a conditional design framework in which preprocessing, architecture, hyperparameter optimization, transfer evaluation, interpretability, and reproducibility are treated as coupled components. Rather than seeking a universally optimal CNN, the framework aims to support physics-aware, shift-aware, and reproducible model comparison in NIR chemometrics.