Development of Self-Supervised Learning with Dinov2-Distilled Models for Parasite Classification in Screening

Simple item page
dc.contributor.authorPinetsuksai, Natchapon
dc.contributor.authorKittichai, Veerayuth
dc.contributor.authorJomtarak, Rangsan
dc.contributor.authorJaksukam, Komgrit
dc.contributor.authorTongloy, Teerawat
dc.contributor.authorBoonsang, Siridech
dc.contributor.authorChuwongin, Santhad
dc.date.accessioned2026-08-06T10:38:56Z
dc.date.available2026-08-06T10:38:56Z
dc.date.issued2023-01-01
dc.description.abstractAt present, parasitic infections in humans, such as intestinal parasitic infections and soil-transmitted helminth (STH) infection, remain a public health concern, with screening methods that are simple but time-consuming and require parasitology experts. Microscopy images are increasingly being used to aid diagnosis but creating labels for supervised learning (SL) is a time-consuming, labor-intensive, and costly process. Self-supervised learning (SSL) is a deep learning approach that aims to train models to represent features in unlabeled datasets using automatically generated labels or annotations from the data itself, rather than explicitly labeled human-labeled labels. It is an appropriate method to address the challenges associated with the difficulty of labeling large datasets. A pretrained model that has learned useful data representations from an SSL task is fine-tuned using labeled data to perform well on a specific downstream task. DINOv2 is an SSL model based on the Vision Transformer (ViT) architecture. In this study, we aim to create a model for screening for helminth egg infection using a fine-tuned Dinov2 with a classification layer head to demonstrate that dataset sizes of 1% and 10% are sufficient when compared to SL model. Rather than SL, which requires a significant amount of human data labeling and is generally impractical, the model developed in this study is expected to be used in active surveillance in the future.
dc.identifier.citation2023 15th International Conference on Information Technology and Electrical Engineering Icitee 2023, 323-328, 2023
dc.identifier.doi10.1109/ICITEE59582.2023.10317719
dc.identifier.other2-s2.0-85179891077
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/13729
dc.source2023 15th International Conference on Information Technology and Electrical Engineering Icitee 2023
dc.subjectBootstrap Your Own Latent (BYOL)
dc.subjectDinov2
dc.subjectObject classification
dc.subjectparasite eggs
dc.subjectSelf-supervised learning (SSL)
dc.titleDevelopment of Self-Supervised Learning with Dinov2-Distilled Models for Parasite Classification in Screening
dc.typeConference Paper

Files

Collections

Research