The Sloop System for Individual Animal Identification with Deep Learning

TL;DR

The Sloop system uses deep learning and relevance feedback to improve individual animal identification from photographs, achieving high recall with shallow networks and demonstrating the importance of expert input.

Contribution

It introduces a novel animal identification system combining adaptive visual features and relevance feedback, outperforming standard deep learning methods.

Findings

Shallow networks with amplitude and deformation features yield superior recognition.

Relevance feedback enhances high-recall performance in animal identification.

Deep learning approaches benefit from relevance feedback for comparable results.

Abstract

The MIT Sloop system indexes and retrieves photographs from databases of non-stationary animal population distributions. To do this, it adaptively represents and matches generic visual feature representations using sparse relevance feedback from experts and crowds. Here, we describe the Sloop system and its application, then compare its approach to a standard deep learning formulation. We then show that priming with amplitude and deformation features requires very shallow networks to produce superior recognition results. Results suggest that relevance feedback, which enables Sloop's high-recall performance may also be essential for deep learning approaches to individual identification to deliver comparable results.