EcoBin: A Two-Stage Deep Convolutional Neural Network for Contamination-Aware Waste Classification

• URL: http://arxiv.org/abs/2606.15547v1
• Date: Sun, 14 Jun 2026 02:20:58 GMT
• Title: EcoBin: A Two-Stage Deep Convolutional Neural Network for Contamination-Aware Waste Classification
• Abstract summary: We present EcoBin, a two-stage deep convolutional neural network that classifies household waste by its disposal pathway.<n>Because no public dataset of contaminated recyclables exists, we synthesize one by segmenting images of clean recyclables with a U2-Net model.<n>On a test set of contaminated recyclables, the complete pipeline routes 24 of 25 items correctly, compared with only 1 of 25 for the base classifier alone.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Waste classification models have become highly accurate at sorting waste, often exceeding 95% on benchmark datasets. However, these models fail to account for contamination in recyclable waste. We present EcoBin, a two-stage deep convolutional neural network that classifies household waste by its disposal pathway and that explicitly accounts for contamination. The first stage is a base waste classifier built on an EfficientNetV2-S backbone that assigns each of the thirty waste categories in our dataset to one of four disposal pathways. The second stage is a contamination classifier that inspects any item routed toward recycling and overrides the decision to garbage when contamination is detected. Because no public dataset of contaminated recyclables exists, we synthesize one by segmenting images of clean recyclable objects with a U2-Net model and compositing realistic contamination textures onto their surfaces. The first stage achieves 87.42% test accuracy and a 96.13% pathway-adjusted accuracy. Meanwhile, the contamination stage distinguishes clean from contaminated items with a 0.99 ROC-AUC. On a test set of contaminated recyclables, the complete pipeline routes 24 of 25 items correctly, compared with only 1 of 25 for the base classifier alone. A McNemar's test confirms that the improvement contributed by the contamination stage is statistically significant (p < 0.001).

Related papers

• SpectralWaste Dataset: Multimodal Data for Waste Sorting Automation [46.178512739789426]
  We present SpectralWaste, the first dataset collected from an operational plastic waste sorting facility. This dataset contains labels for several categories of objects that commonly appear in sorting plants. We propose a pipeline employing different object segmentation architectures and evaluate the alternatives on our dataset.
  arXiv  Detail & Related papers  (2024-03-26T18:39:38Z)
• VisDA 2022 Challenge: Domain Adaptation for Industrial Waste Sorting [61.52419223232737]
  In industrial waste sorting, one of the biggest challenges is the extreme diversity of the input stream. We present the VisDA 2022 Challenge on Domain Adaptation for Industrial Waste Sorting.
  arXiv  Detail & Related papers  (2023-03-26T21:38:38Z)
• A Method for Waste Segregation using Convolutional Neural Networks [0.0]
  In this paper, we try to use deep learning algorithms to help solve this problem of waste classification. Our proposed model achieves an accuracy of 94.9%.
  arXiv  Detail & Related papers  (2022-02-23T14:32:10Z)
• Classification of PS and ABS Black Plastics for WEEE Recycling Applications [63.942632088208505]
  This work is aimed at creating a system that can classify different types of plastics by using picture analysis, in particular, black plastics of the type Polystyrene (PS) and Acrylonitrile Butadiene Styrene (ABS) A Convolutional Neural Network has been tested and retrained, obtaining a validation accuracy of 95%. Using a separate test set, average accuracy goes down to 86.6%, but a further look at the results shows that the ABS type is correctly classified 100% of the time, so it is the PS type that accumulates all the errors.
  arXiv  Detail & Related papers  (2021-10-20T12:47:18Z)
• ZeroWaste Dataset: Towards Automated Waste Recycling [51.053682077915546]
  We present the first in-the-wild industrial-grade waste detection and segmentation dataset, ZeroWaste. This dataset contains over1800fully segmented video frames collected from a real waste sorting plant. We show that state-of-the-art segmentation methods struggle to correctly detect and classify target objects.
  arXiv  Detail & Related papers  (2021-06-04T22:17:09Z)
• Waste detection in Pomerania: non-profit project for detecting waste in environment [0.0]
  Litter is classified into seven categories: bio, glass, metal and plastic, non-recyclable, other, paper and unknown. Our approach achieves up to 70% of average precision in waste detection and around 75% of classification accuracy on the test dataset.
  arXiv  Detail & Related papers  (2021-05-12T09:33:22Z)
• Unassisted Noise Reduction of Chemical Reaction Data Sets [59.127921057012564]
  We propose a machine learning-based, unassisted approach to remove chemically wrong entries from data sets. Our results show an improved prediction quality for models trained on the cleaned and balanced data sets.
  arXiv  Detail & Related papers  (2021-02-02T09:34:34Z)
• DeepWaste: Applying Deep Learning to Waste Classification for a Sustainable Planet [0.0]
  Current attempts to reduce erroneous waste disposal are expensive, inaccurate, and confusing. We propose DeepWaste, a mobile app that utilizes highly optimized deep learning techniques to provide users instantaneous waste classification into trash, recycling, and compost. Our best model, a deep learning residual neural network with 50 layers, achieves an average precision of 0.881 on the test set.
  arXiv  Detail & Related papers  (2021-01-15T04:06:25Z)
• One-Shot Learning with Triplet Loss for Vegetation Classification Tasks [45.82374977939355]
  Triplet loss function is one of the options that can significantly improve the accuracy of the One-shot Learning tasks. Starting from 2015, many projects use Siamese networks and this kind of loss for face recognition and object classification.
  arXiv  Detail & Related papers  (2020-12-14T10:44:22Z)
• Comparative Analysis of Multiple Deep CNN Models for Waste Classification [0.0]
  The project tested well known Deep Learning Network architectures for waste classification with dataset combined from own endeavors and Trash Net. The hardware built in the form of dustbin is used to segregate those wastes into different compartments.
  arXiv  Detail & Related papers  (2020-04-05T11:50:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.