DEEPFIN: A deep learning tool for fish image classification from unlabeled data
Summary Automating fish image classification would relieve a growing annotation bottleneck in ecology, developmental biology, and fisheries science, where imagery accumulates far faster than experts can label it. We present DEEPFIN, an annotation-free image analysis pipeline that combines foreground segmentation, frozen pretrained convolutional encoders, non-linear dimensionality reduction, and density-based clustering. DEEPFIN recovers the seven canonical developmental stages of the clownfish Amphiprion ocellaris with 87% cluster-to-class accuracy and separates three congeneric anemonefish species from images alone. Independent validation across three public datasets spanning in situ underwater, multi-condition, and controlled ground-truth-masked imaging yields consistent pairwise species discrimination without labels, matching or approaching contemporary supervised methods on the same data. Beyond replicating expert categories, the pipeline surfaces intra-class variation that fixed-label classifiers cannot expose. DEEPFIN is a lightweight, generalizable framework for extracting biological structure from the growing volumes of unlabeled fish imagery.