Underwater instance segmentation models are typically trained and evaluated on a single dataset, leaving cross-dataset generalization unstudied. This project measures the cross-dataset domain gap between TrashCan (7,212 deep-sea ROV images, 22 classes) and SeaClear (8,610 shallow-water images, 40 classes) using Mask R-CNN with a COCO-pretrained ResNet-50 FPN backbone. Models trained on one dataset fail catastrophically on the other despite overlapping object categories. We show this gap is visual, not semantic: silhouette analysis of backbone features reveals strong dataset clustering even at the per-class level. To mitigate the gap, we pool both datasets into common category spaces via a generic coarsening hierarchy and show that a single pooled model recovers or exceeds in-domain performance on both test sets. We also re-split TrashCan using frame-chunking to fix data leakage in the original split. All results are explorable via an interactive Streamlit dashboard.

A polyp is an abnormal tissue growth in the large intestine that is typically benign but can develop into malignant colorectal cancer. Colonoscopy enables endoscopists to identify and assess these polyps for potential removal. However, the accuracy of this procedure depends heavily on the clinician’s expertise, making it prone to human error and variability. Our goal is to build a deep-learning model that detects colorectal polyps in images from colonoscopies to minimize missed lesions and improve patient outcomes.