Semi-Supervised Learning-Based Live Fish Identification in Aquaculture UsingModified Deep Convolutional Generative Adversarial Networks

摘要

Aiming at live fish identification in aquaculture, a practical and efficient semi-supervised learning model, based on modified deep convolutional generative adversarial networks (DCGANs), was proposed in this study. Benefiting from the modified DCGANsstructure, the presented model can be trained effectively using relatively few labeled training samples. In consideration of the complex poses offish and the low resolution ofsampling images in aquaculture, spatial pyramid pooling and some improved techniques specifically for the presented model were used to make the model more robust. Finally, in tests with two preprocessed and challenging datasets (with 5%, 10%, and 15% labeled training data in the fish recognition ground-truth dataset and 25%, 50%,and 75% labeled training data in the Croatian fish dataset), the feasibility and reliability of the presented modelfor live fish identification were proved with respective accuracies of80.52%, 81.66%, and 83.07% for the ground-truth dataset and 65.13%, 78.72%, and 82.95% for the Croatian fish dataset.