# Multi-Modal Semantic Segmentation of Electrolyzer Components for Sustainable Hydrogen Technologies: A Dual-Branch Deep Learning Approach

arXiv: https://arxiv.org/abs/2607.16056 · HTML: https://mlsanity.com/paper/2607.16056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 53 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation](https://mlsanity.com/paper/2102.04525/) (2021)
- [RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation](https://mlsanity.com/paper/1806.01054/) (2018)
- [PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions](https://mlsanity.com/paper/2204.12511/) (2022)
- [Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions](https://mlsanity.com/paper/2308.14263/) (2023)
- [Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition](https://mlsanity.com/paper/2112.10992/) (2021)
- [Hyperspectral Image Denoising and Anomaly Detection Based on Low-rank and Sparse Representations](https://mlsanity.com/paper/2103.07437/) (2021)
- [Generative AI in Industrial Machine Vision -- A Review](https://mlsanity.com/paper/2408.10775/) (2024)
- [Hyperspectral Band Selection for Multispectral Image Classification with Convolutional Networks](https://mlsanity.com/paper/2106.00645/) (2021)
- [PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards](https://mlsanity.com/paper/2401.06528/) (2024)
- [Hyperspectral Dataset and Deep Learning methods for Waste from Electric and Electronic Equipment Identification (WEEE)](https://mlsanity.com/paper/2407.04505/) (2024)
- [Domestic waste detection and grasping points for robotic picking up](https://mlsanity.com/paper/2105.06825/) (2021)
- [WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks](https://mlsanity.com/paper/2409.16999/) (2024)
- [Electrolyzers-HSI: Close-Range Multi-Scene Hyperspectral Imaging Benchmark Dataset](https://mlsanity.com/paper/2505.20507/) (2025)
- [An Ensemble Learning Approach towards Waste Segmentation in Cluttered Environment](https://mlsanity.com/paper/2602.13681/) (2026)

## Abstract (arXiv)

Accurate segmentation of electrolyzer materials is essential for automated disassembly, sustainable recycling, and circular manufacturing in hydrogen technologies. However, this task is challenging due to strong visual similarity between materials, spectral overlap, irregular shapes, and severe class imbalance. To address these challenges, we propose an AI-driven dual-branch framework, Hyperspectral-RGB Electrolyzer Materials Network (HREM-Net), that combines hyperspectral imaging (HSI) and RGB images for electrolyzer material segmentation. We implemented several innovative modules, including Efficient Channel Attention, Coordinate Attention, Mobile Inverted Bottleneck blocks, and Atrous Spatial Pyramid Pooling to capture spectral and spatial features from HSI, and RGB images. With an adaptive gated cross-modal fusion module and composite loss function, HREM-Net achieves a mean class accuracy of 91.66% and a mean Intersection over Union (mIoU) of 0.82 on the Electrolyzers-HSI dataset, outperforming baseline segmentation models. Cross-dataset validation on the PCB-Vision dataset demonstrates strong generalization with 96.91% accuracy and 0.93 mIoU. This work poses its potential as an industrial application to improve electrolyzer efficiency, thereby improving the predictive maintenance of hydrogen production.