FusionSort: Enhanced Cluttered Waste Segmentation with Advanced Decoding and Comprehensive Modality Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909755426996224 |
|---|---|
| author | Ali, Muhammad AlSuwaidi, Omar Ali |
| author_facet | Ali, Muhammad AlSuwaidi, Omar Ali |
| contents | In the realm of waste management, automating the sorting process for non-biodegradable materials presents considerable challenges due to the complexity and variability of waste streams. To address these challenges, we introduce an enhanced neural architecture that builds upon an existing Encoder-Decoder structure to improve the accuracy and efficiency of waste sorting systems. Our model integrates several key innovations: a Comprehensive Attention Block within the decoder, which refines feature representations by combining convolutional and upsampling operations. In parallel, we utilize attention through the Mamba architecture, providing an additional performance boost. We also introduce a Data Fusion Block that fuses images with more than three channels. To achieve this, we apply PCA transformation to reduce the dimensionality while retaining the maximum variance and essential information across three dimensions, which are then used for further processing. We evaluated the model on RGB, hyperspectral, multispectral, and a combination of RGB and hyperspectral data. The results demonstrate that our approach outperforms existing methods by a significant margin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19798 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FusionSort: Enhanced Cluttered Waste Segmentation with Advanced Decoding and Comprehensive Modality Optimization Ali, Muhammad AlSuwaidi, Omar Ali Computer Vision and Pattern Recognition In the realm of waste management, automating the sorting process for non-biodegradable materials presents considerable challenges due to the complexity and variability of waste streams. To address these challenges, we introduce an enhanced neural architecture that builds upon an existing Encoder-Decoder structure to improve the accuracy and efficiency of waste sorting systems. Our model integrates several key innovations: a Comprehensive Attention Block within the decoder, which refines feature representations by combining convolutional and upsampling operations. In parallel, we utilize attention through the Mamba architecture, providing an additional performance boost. We also introduce a Data Fusion Block that fuses images with more than three channels. To achieve this, we apply PCA transformation to reduce the dimensionality while retaining the maximum variance and essential information across three dimensions, which are then used for further processing. We evaluated the model on RGB, hyperspectral, multispectral, and a combination of RGB and hyperspectral data. The results demonstrate that our approach outperforms existing methods by a significant margin. |
| title | FusionSort: Enhanced Cluttered Waste Segmentation with Advanced Decoding and Comprehensive Modality Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.19798 |