Marine Animal Detection and Recognition with Advanced Deep Learning Models

This paper summarizes SIATMMLAB’s contributions in SEACLEF2017 task [1]. We took part in three subtasks with advanced deep learning models. In Automatic Fish Identification and Species Recognition task, we exploited different frameworks to detect the proposal boxes of foreground fish, then fine-tuned a pre-trained neural network to classify the fish. In Automatic Frame-level Salmon Identification task, we utilized the BN-Inception [2] network to identify whether a video frame contains salmons or not. In Marine Animal Recognition task, we examined different neural networks to make classification based on weakly-labelled images. Our methods achieve good results in both task1 and task3.