How to Track and Segment Fish without Human Annotations: A Self-Supervised Deep Learning Approach

TL;DR

This paper introduces a self-supervised deep learning method for fish tracking and segmentation in underwater videos that does not require human annotations, leveraging pseudo-labels generated from video data.

Contribution

The authors develop a novel unsupervised framework combining optical flow and self-supervised learning to train fish segmentation models without manual labels.

Findings

Effective fish segmentation demonstrated on three public datasets

Robustness to varying imaging conditions validated

Reduces need for costly manual annotations

Abstract

Tracking fish movements and sizes of fish is crucial to understanding their ecology and behaviour. Knowing where fish migrate, how they interact with their environment, and how their size affects their behaviour can help ecologists develop more effective conservation and management strategies to protect fish populations and their habitats. Deep learning is a promising tool to analyze fish ecology from underwater videos. However, training deep neural networks (DNNs) for fish tracking and segmentation requires high-quality labels, which are expensive to obtain. We propose an alternative unsupervised approach that relies on spatial and temporal variations in video data to generate noisy pseudo-ground-truth labels. We train a multitask DNN using these pseudo-labels. Our framework consists of three stages: (1) an optical flow model generates the pseudo labels using spatial and temporal consistency between frames, (2) a self-supervised model refines the pseudo-labels incrementally, and (3) a segmentation network uses the refined labels for training. Consequently, we perform extensive experiments to validate our method on three public underwater video datasets and demonstrate its effectiveness for video annotation and segmentation. We also evaluate its robustness to different imaging conditions and discuss its limitations.