{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:21:51Z","timestamp":1784391711169,"version":"3.55.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Efficient waste management is crucial for urban environments to maintain cleanliness, reduce environmental impact, and optimize resource allocation. Traditional waste collection systems often rely on scheduled pickups or manual inspections, leading to inefficient resource utilization and potential overflow issues. This paper presents a novel approach to automate the detection of garbage container fullness from images using machine learning techniques. More specifically, we explore three transformer-based architectures, namely, vision transformer, Swin transformer, and pyramid vision transformer to classify input images of garbage bins as clean or dirty. Our experimental results on the publicly available Clean dirty containers in Montevideo dataset suggest that transformer-based architectures are effective in garbage fullness detection. Moreover, a comparison with existing methods reveals that the proposed approach using the vision transformer surpasses the state-of-the-art, achieving a 96.74% accuracy in detecting garbage container fullness. In addition, the generalizability of the proposed approach is evaluated by testing the transformer-based classification frameworks on a synthetic image dataset generated using various generative AI models. The proposed approach achieved a highest test accuracy of 80% on this synthetic dataset, thereby highlighting its ability to generalize across different datasets. Synthetic dataset used in this work can be found at: <jats:ext-link>https:\/\/www.kaggle.com\/datasets\/6df0652d2c4eb3b9f00043c40fba0afa0778b46d7c0685e212807c2f6967fe6f<\/jats:ext-link>.<\/jats:p>","DOI":"10.3389\/frai.2025.1612080","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T14:31:06Z","timestamp":1757428266000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluation of vision transformers for the detection of fullness of garbage bins for efficient waste management"],"prefix":"10.3389","volume":"8","author":[{"given":"Parakram Singh","family":"Tanwer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shishir","family":"Maheshwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sushree","family":"Behera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amit","family":"Chauhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T.","family":"Sunil Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"B1","unstructured":"Hugging face\n          \n          2024"},{"key":"B2","doi-asserted-by":"publisher","first-page":"16024","DOI":"10.1038\/s41598-025-99885-x","article-title":"Real time intelligent garbage monitoring and efficient collection using yolov8 and yolov5 deep learning models for environmental sustainability","volume":"15","author":"Abozahhad","year":"2025","journal-title":"Sci. Rep"},{"key":"B3","doi-asserted-by":"publisher","first-page":"96495","DOI":"10.1109\/ACCESS.2020.2995681","article-title":"Intelligent fusion of deep features for improved waste classification","volume":"8","author":"Ahmad","year":"2020","journal-title":"IEEE Access"},{"key":"B4","unstructured":"AI\n              M.\n            \n          \n          Llama 3.1 responsible use guide\n          \n          2025"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICIICT1.2019.8741499","author":"Aravindaraman","year":"2019"},{"key":"B6","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/s10462-023-10646-6","article-title":"A survey of smart dustbin systems using the IoT and deep learning","volume":"57","author":"Arthur","year":"2024","journal-title":"Artif. Intell. Rev"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1109\/FRUCT.2014.6872422","article-title":"\u201cAn approach for monitoring and smart planning of urban solid waste management using smart-m3 platform,\u201d","author":"Catania","year":"2014","journal-title":"Proceedings of 15th Conference of Open Innovations Association FRUCT"},{"key":"B8","doi-asserted-by":"publisher","first-page":"84095","DOI":"10.1007\/s11042-024-18939-w","article-title":"Intelligent waste classification approach based on improved multi-layered convolutional neural network","volume":"83","author":"Chhabra","year":"2024","journal-title":"Multimed. Tools Appl"},{"key":"B9","doi-asserted-by":"publisher","first-page":"8146","DOI":"10.3390\/app10228146","article-title":"An energy saving road sweeper using deep vision for garbage detection","volume":"10","author":"Donati","year":"2019","journal-title":"Appl. Sci"},{"key":"B10","article-title":"\u201cAn image is worth 16x16 words: Transformers for image recognition at scale,\u201d","author":"Dosovitskiy","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"B11","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1109\/72.165600","article-title":"Improving generalization performance using double backpropagation","volume":"3","author":"Drucker","year":"1992","journal-title":"IEEE Trans. Neural Netw"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1950","DOI":"10.1016\/j.procs.2020.03.222","article-title":"Household waste management system using iot and machine learning","volume":"167","author":"Dubey","year":"2020","journal-title":"Procedia Comput. Sci"},{"key":"B13","article-title":"Gemini: A family of highly capable multimodal models","author":"Gemini","year":"2025","journal-title":"arXiv preprint arXiv:2312.11805"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2861","DOI":"10.3390\/rs14122861","article-title":"Swin-transformer-enabled yolov5 with attention mechanism for small object detection on satellite images","volume":"14","author":"Gong","year":"2022","journal-title":"Rem. Sens"},{"key":"B15","article-title":"A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation","author":"Gotmare","year":"2018","journal-title":"arXiv preprint arXiv:1810.13243"},{"key":"B16","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/s42979-020-00312-x","article-title":"Layerout: freezing layers in deep neural networks","volume":"1","author":"Goutam","year":"2020","journal-title":"SN Comput. Sci"},{"key":"B17","first-page":"272","article-title":"\u201cSwin unetr: Swin transformers for semantic segmentation of brain tumors in MRI images,\u201d","volume-title":"International MICCAI Brainlesion Workshop","author":"Hatamizadeh","year":"2021"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","article-title":"\u201cDeep residual learning for image recognition,\u201d","author":"He","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3202036","article-title":"A 3-D-swin transformer-based hierarchical contrastive learning method for hyperspectral image classification","volume":"60","author":"Huang","year":"2022","journal-title":"IEEE Trans. Geosci. Rem. Sens"},{"key":"B20","unstructured":"Laguna\n              R.\n            \n          \n          Clean dirty containers in montevideo\n          \n          2021"},{"key":"B21","article-title":"\u201cContainers in montevideo: a multi source image dataset,\u201d","author":"Laguna","year":"2021","journal-title":"XXII Simposio Argentino de Inteligencia artificial (ASSAI 2021)-JAIIO 50 (Modalidad virtual)"},{"key":"B22","first-page":"21","article-title":"\u201cA theoretical framework for back-propagation,\u201d","author":"LeCun","year":"1988","journal-title":"Proceedings of the 1988 Connectionist Models Summer School"},{"key":"B23","doi-asserted-by":"publisher","first-page":"29505","DOI":"10.1007\/s11042-023-16677-z","article-title":"A smart waste classification model using hybrid CNN-LSTM with transfer learning for sustainable environment","volume":"83","author":"Lilhore","year":"2024","journal-title":"Multimed. Tools Appl"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170","article-title":"Swin transformer V2: scaling up capacity and resolution","author":"Liu","year":"","journal-title":"CoRR, abs\/2111.09883"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"\u201cSwin transformer: Hierarchical vision transformer using shifted windows,\u201d","author":"Liu","year":"","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"B26","doi-asserted-by":"publisher","first-page":"79","DOI":"10.15623\/ijret.2016.0506016","article-title":"A review: Garbage collection management system","volume":"5","author":"Lokhande","year":"2016","journal-title":"Int. J. Res. Eng. Technol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"8278","DOI":"10.3390\/s21248278","article-title":"A 5G -enabled smart waste management system for university campus","volume":"21","author":"Longo","year":"2021","journal-title":"Sensors"},{"key":"B28","unstructured":"Hugging face\n          \n          2024"},{"key":"B29","doi-asserted-by":"publisher","first-page":"113028","DOI":"10.1016\/j.knosys.2025.113028","article-title":"An automated waste classification system using deep learning techniques: toward efficient waste recycling and environmental sustainability","volume":"310","author":"Nahiduzzaman","year":"2025","journal-title":"Knowl. Based Syst"},{"key":"B30","doi-asserted-by":"publisher","first-page":"113028","DOI":"10.1016\/j.knosys.2025.113028","article-title":"An automated waste classification system using deep learning techniques: Toward efficient waste recycling and environmental sustainability","volume":"310","author":"Nahiduzzaman","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"B31","doi-asserted-by":"publisher","first-page":"119544","DOI":"10.1016\/j.eswa.2023.119544","article-title":"Determining the fullness of garbage containers by deep learning","volume":"217","author":"O\u011fuz","year":"2023","journal-title":"Expert Syst. Appl"},{"key":"B32","article-title":"Gpt-4 technical report","year":"2024","journal-title":"arXiv preprint arXiv:2303.08774"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18265-1","article-title":"Nuni-waste: novel semi-supervised semantic segmentation waste classification with non-uniform data augmentation","author":"Qi","year":"2024","journal-title":"Multim. Tools Applic"},{"key":"B34","article-title":"Imagenet-21k pretraining for the masses","author":"Ridnik","year":"2021","journal-title":"arXiv preprint arXiv:2104.10972"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74","article-title":"\u201cGrad-cam: visual explanations from deep networks via gradient-based localization,\u201d","author":"Selvaraju","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"B36","first-page":"1","article-title":"\u201cSmart garbage segregation &management system using internet of things (IoT) &machine learning (ml),\u201d","volume-title":"2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT)","author":"Shamin","year":"2019"},{"key":"B37","first-page":"1086","article-title":"\u201cDeep learning based smart garbage classifier for effective waste management,\u201d","volume-title":"2020 5th International Conference on Communication and Electronics Systems (ICCES)","author":"Sidharth","year":"2020"},{"key":"B38","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"B39","doi-asserted-by":"publisher","first-page":"100255","DOI":"10.1016\/j.iot.2020.100255","article-title":"Smart garbage management system for a sustainable urban life: an IoT based application","volume":"11","author":"Sohag","year":"2020","journal-title":"Internet Things"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/su17093922","article-title":"A garbage detection and classification model for orchards based on lightweight yolov7","volume":"17","author":"Tian","year":"2025","journal-title":"Sustainability"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061","article-title":"\u201cPyramid vision transformer: a versatile backbone for dense prediction without convolutions,\u201d","author":"Wang","year":"2021","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.8090","article-title":"\u201cHeterogeneous transfer learning for image classification,\u201d","author":"Zhu","year":"2011","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1612080\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T14:31:17Z","timestamp":1757428277000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1612080\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":42,"alternative-id":["10.3389\/frai.2025.1612080"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1612080","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,9]]},"article-number":"1612080"}}