Towards Visual Re-Identification of Fish using Fine-Grained Classification for Electronic Monitoring in Fisheries

TL;DR

This paper presents a deep learning pipeline utilizing Vision Transformers and specialized training strategies for automated fish re-identification in electronic monitoring systems, significantly improving accuracy on a novel dataset.

Contribution

It introduces a new AutoFish dataset and demonstrates that combining hard triplet mining with dataset-specific normalization enhances fish re-identification performance.

Findings

Vision Transformer (Swin-T) outperforms ResNet-50 in accuracy.

Hard triplet mining improves re-identification metrics.

Viewpoint variation is a major challenge in distinguishing similar fish.

Abstract

Accurate fisheries data are crucial for effective and sustainable marine resource management. With the recent adoption of Electronic Monitoring (EM) systems, more video data is now being collected than can be feasibly reviewed manually. This paper addresses this challenge by developing an optimized deep learning pipeline for automated fish re-identification (Re-ID) using the novel AutoFish dataset, which simulates EM systems with conveyor belts with six similarly looking fish species. We demonstrate that key Re-ID metrics (R1 and mAP@k) are substantially improved by using hard triplet mining in conjunction with a custom image transformation pipeline that includes dataset-specific normalization. By employing these strategies, we demonstrate that the Vision Transformer-based Swin-T architecture consistently outperforms the Convolutional Neural Network-based ResNet-50, achieving peak performance of 41.65% mAP@k and 90.43% Rank-1 accuracy. An in-depth analysis reveals that the primary challenge is distinguishing visually similar individuals of the same species (Intra-species errors), where viewpoint inconsistency proves significantly more detrimental than partial occlusion. The source code and documentation are available at: https://github.com/msamdk/Fish_Re_Identification.git