Patch Ensembles for Robust Salmon Re-Identification with Weak Trajectory Labels

TL;DR

This paper introduces a patch-based re-identification framework for salmon in commercial net-pens, utilizing ensemble methods and texture features to improve accuracy and robustness across different camera views.

Contribution

The authors propose a novel patch ensemble approach that leverages texture-anchored patches and a new multi-camera dataset for robust salmon re-identification.

Findings

Ensemble approach improves cross-camera mAP from 0.609 to 0.860.

Patch-based method outperforms full-image baseline in validation and cross-camera tests.

Texture-anchored patches enable better generalization across different viewpoints.

Abstract

Salmon re-identification in commercial net-pens is challenging due to large populations, which impose strict accuracy requirements and make large-scale labeled data acquisition infeasible. Trajectory IDs can be used as proxy labels, but this introduces trajectory-ID bias. To address these challenges, we propose a patch-based re-identification framework that fuses patch-level predictions into a salmon identity decision. A key component is the prediction of the salmon's lateral line, enabling extraction of texture-anchored patches and patch slices. To enable realistic evaluation, we introduce an experimental setup using multiple cameras placed 6 m apart, allowing the same fish to be recorded in different trajectories. This enables the construction of a cross-camera test set through manual match confirmation. Our ensemble approach outperforms the full-image baseline in same-trajectory validation (0.932 to 0.965 mAP) and cross-camera testing (0.609 to 0.860 mAP). The substantial improvements in the cross-camera setting demonstrate improved generalizability and robustness. Code and data: https://github.com/espenbh/salmon-reid-patch-ensemble.