MARATTO

dataset · Zenodo (CERN European Organization for Nuclear Research)

Curated Mixed Plastic Waste Instance Segmentation Dataset with Annotations

2026Open accessOctober 6 University

Abstract

This dataset contains manually curated, instance-level annotated images of mixed plastic waste for instance segmentation. The annotated classes are PET_Bottle, PET_Container, PET_Cup, HDPE_Bottle, HDPE_Tshirt_Bag, LDPE_Garbage, PP_Bottle_Container, and PS_Cup_Container. The dataset was prepared through curation, class harmonization, and annotation to support model training and evaluation for mixed plastic waste analysis.Note: The exported dataset version contained 3,188 images. After automated integrity verification and coding-related validation, four files were excluded, resulting in a final validated set of 3,184 images used in the experiments.

Read the original research

This page summarises published work. The authoritative version sits with the publisher.

DOI: 10.5281/zenodo.19464639

Is something wrong with this record? Report it or request removal.

Discussion

Discuss this research

Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.

No discussion yet. Open the first thread.