Improving pseudo-labelling for semi-supervised single-class instance segmentation via mask symmetry scoring

• Architecture-invariant prediction mask metric for pseudo-labelling assessment. • Outperforms state-of-the-art on single-class segmentation in agri-robotic dataset. • Comparable to state-of-the-art on multi-class benchmarks, showing generalisability. • Publishes real-world agri dataset/ for single-class segmentation with code/models. Semi-supervised teacher-student pseudo-labelling improves instance segmentation by exploiting unlabelled data, where a teacher network, trained with a small annotated dataset, generates pseudo labels for the remaining data, to train the student model. However, mask selection typically relies heavily on the class confidence scores. In single-class settings these scores saturate, offering little discrimination between masks. In this work we propose a mask symmetry score that evaluates logits from the mask prediction head, enabling more reliable pseudo-label selection without architectural changes. Evaluations on both CNN- and Transformer-based models show our method outperforms state-of-the-art approaches on a real-world agri-robotic dataset of densely clustered potato tubers.