Title of master thesis: Weakly semi-supervised object detection for annotation efficiency: Leveraging a mix of strong bounding box labels and weak point labels for detecting coffee berry disease
Password Zoom: 948004
Overview
- Date:Starts 8 November 2023, 13:00Ends 8 November 2023, 14:00
- Location:von Bahr, Soliden GU Physics
- Language:English
Abstract: Annotating datasets is a common obstacle for many industries with the potential for adopting machine learning methods. One example of such an industry is agriculture. Resources may be limited, especially in developing areas, but there is great potential for machine learning models to be used when tracking diseases for example. This work revolves around developing an efficient machine learning pipeline and using it to detect coffee berry disease (CBD) in a dataset with images of coffee plants. CBD is a fungal plant pathogen that is difficult to manage and often causes major problems for coffee production.Three common methods to alleviate the burden of manually annotating datasets are semi-supervised learning, weak supervision, and utilizing machine learning in the labelling process. Recently developed open-set detectors that boast impressive performance have a natural use case in this process. These models can predict bounding boxes for arbitrary objects without specific training and can therefore be used to generate proposals for ground truth bounding boxes in a dataset. Following this initial step, manually annotating time-efficient point labels for the remaining objects in each image results in a mix of strong box labels and weak point labels in each image. This work explores this setting and proposes two models for the task; Point-guided loss suppression (PLS) and mixed Point-Teaching (MPT). The PLS model is a simple adaptation of YOLOv8, which when compared to the semi-supervised case gives a slight improvement in performance on the CBD dataset and a slight decrease in the MS COCO benchmark. The MPT framework consists of two models, one that generates boxes that the other uses as pseudo labels during training. The resulting performance for the MPT framework is generally worse, only performing above the baseline in a few cases. The exact efficiency of utilizing point labels is difficult to determine, but our results indicate that there are potential use cases where annotating points is more efficient than boxes, especially with further development of the models.
Supervisors: Olof Mogren, Aleksis Pirinen
Examiner: Mats Granath
Opponent: Anton Sandberg