# FusionSort: Enhanced Cluttered Waste Segmentation with Advanced Decoding and Comprehensive Modality Optimization

arXiv: https://arxiv.org/abs/2508.19798 · HTML: https://mlsanity.com/paper/2508.19798/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 29 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 7 of 7)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.04838/) (2022)
- [Cross-Entropy Loss Functions: Theoretical Analysis and Applications](https://mlsanity.com/paper/2304.07288/) (2023)
- [SpectralWaste Dataset: Multimodal Data for Waste Sorting Automation](https://mlsanity.com/paper/2403.18033/) (2024)
- [Enhancing Environmental Monitoring through Multispectral Imaging: The WasteMS Dataset for Semantic Segmentation of Lakeside Waste](https://mlsanity.com/paper/2407.17028/) (2024)

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

- [Bidirectional Cross-Attention Fusion of High-Resolution RGB and Low-Resolution Hyperspectral Inputs for Multimodal Semantic Segmentation](https://mlsanity.com/paper/2603.13941/) (2026)

## Abstract (arXiv)

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.