# Resource Constrained Semantic Segmentation for Waste Sorting

arXiv: https://arxiv.org/abs/2310.19407 · HTML: https://mlsanity.com/paper/2310.19407/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 8 of 8)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [TACO: Trash Annotations in Context for Litter Detection](https://mlsanity.com/paper/2003.06975/) (2020)

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

- [COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes](https://mlsanity.com/paper/2410.24139/) (2024)

## Abstract (arXiv)

This work addresses the need for efficient waste sorting strategies in Materials Recovery Facilities to minimize the environmental impact of rising waste. We propose resource-constrained semantic segmentation models for segmenting recyclable waste in industrial settings. Our goal is to develop models that fit within a 10MB memory constraint, suitable for edge applications with limited processing capacity. We perform the experiments on three networks: ICNet, BiSeNet (Xception39 backbone), and ENet. Given the aforementioned limitation, we implement quantization and pruning techniques on the broader nets, achieving positive results while marginally impacting the Mean IoU metric. Furthermore, we propose a combination of Focal and Lov'asz loss that addresses the implicit class imbalance resulting in better performance compared with the Cross-entropy loss function.