Enhancing Understanding Through Wildlife Re-Identification

TL;DR

This paper evaluates various machine learning models, including MLPs, DCNNs, and LightGBM, for wildlife re-identification, highlighting the challenges and inconsistencies in replicating prior research results.

Contribution

It provides a comparative analysis of different models and implementation approaches for wildlife re-identification, emphasizing the importance of suitable loss functions and model configurations.

Findings

MLPs with embedding layers were ineffective for this task.

DCNNs showed inconsistent performance across datasets.

LightGBM overfitted and did not outperform simple baselines.

Abstract

We explore the field of wildlife re-identification by implementing an MLP from scratch using NumPy, A DCNN using Keras, and a binary classifier with LightGBM for the purpose of learning for an assignment. Analyzing the performance of multiple models on multiple datasets. We attempt to replicate prior research in metric learning for wildlife re-identification. Firstly, we find that the usage of MLPs trained for classification, then removing the output layer and using the second last layer as an embedding was not a successful strategy for similar learning; it seems like losses designed for embeddings such as triplet loss are required. The DCNNS performed well on some datasets but poorly on others, which did not align with findings in previous literature. The LightGBM classifier overfitted too heavily and was not significantly better than a constant model when trained and evaluated on all pairs using accuracy as a metric. The technical implementations used seem to match standards according to comparisons with documentation examples and good results on certain datasets. However, there is still more to explore in regards to being able to fully recreate past literature.