{"ID":2862623,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25964","arxiv_id":"2509.25964","title":"Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy","abstract":"Autonomous Raman instruments on Mars rovers, deep-sea landers, and field robots must interpret raw spectra distorted by fluorescence baselines, peak shifts, and limited ground-truth labels. Using curated subsets of the RRUFF database, we evaluate one-dimensional convolutional neural networks (CNNs) and report four advances: (i) Baseline-independent classification: compact CNNs surpass $k$-nearest-neighbors and support-vector machines on handcrafted features, removing background-correction and peak-picking stages while ensuring reproducibility through released data splits and scripts. (ii) Pooling-controlled robustness: tuning a single pooling parameter accommodates Raman shifts up to $30 \\,\\mathrm{cm}^{-1}$, balancing translational invariance with spectral resolution. (iii) Label-efficient learning: semi-supervised generative adversarial networks and contrastive pretraining raise accuracy by up to $11\\%$ with only $10\\%$ labels, valuable for autonomous deployments with scarce annotation. (iv) Constant-time adaptation: freezing the CNN backbone and retraining only the softmax layer transfers models to unseen minerals at $\\mathcal{O}(1)$ cost, outperforming Siamese networks on resource-limited processors. This workflow, which involves training on raw spectra, tuning pooling, adding semi-supervision when labels are scarce, and fine-tuning lightly for new targets, provides a practical path toward robust, low-footprint Raman classification in autonomous exploration.","short_abstract":"Autonomous Raman instruments on Mars rovers, deep-sea landers, and field robots must interpret raw spectra distorted by fluorescence baselines, peak shifts, and limited ground-truth labels. Using curated subsets of the RRUFF database, we evaluate one-dimensional convolutional neural networks (CNNs) and report four adva...","url_abs":"https://arxiv.org/abs/2509.25964","url_pdf":"https://arxiv.org/pdf/2509.25964v1","authors":"[\"Deniz Soysal\",\"Xabier García-Andrade\",\"Laura E. Rodriguez\",\"Pablo Sobron\",\"Laura M. Barge\",\"Renaud Detry\"]","published":"2025-09-30T09:01:38Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"LoRA\",\"Convolutional Neural Network\"]","has_code":false}