Abstract
Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification. This dependence on annotated data has driven the curation of numerous large-scale wildlife datasets. This study investigates self-supervised learning Self-Supervised Learning (SSL) for wildlife re-identification. We automatically extract two distinct views of an individual using temporal image pairs from camera trap data without supervision. The image pairs train a self-supervised model from a potentially endless stream of video data. We evaluate the learnt representations against supervised features on open-world scenarios and transfer learning in various wildlife downstream tasks. The analysis of the experimental results shows that self-supervised models are more robust even with limited data. Moreover, self-supervised features outperform supervision across all downstream tasks. The code is available here this https URL.
Abstract (translated)
野生动物再识别的目标是在不同的观测中匹配同一物种的个体。当前最先进的（SOTA）模型依赖于类别标签来训练用于个体分类的监督模型。这种对标注数据的依赖推动了大量大型野生动物数据集的整理。本研究探讨了无监督自监督学习（Self-Supervised Learning, SSL）在野生动物再识别中的应用。我们利用摄像陷阱数据中成对的时间图像，自动提取每个个体的两个不同视角，而无需任何监督。这些图像对可以从潜在无限的视频流数据集中训练出一个自监督模型。 我们在开放世界场景和各种野生动物下游任务的迁移学习上评估了所学表示与监督特征的表现。实验结果分析表明，在有限的数据下，自监督模型更加稳健，并且在所有下游任务中，无监督特征的表现均优于监督方法。相关代码可在[此处](此链接应为一个指向具体代码仓库或项目的URL)获取。 请注意，原文中的“this https URL”是一个占位符，你需要将它替换为实际的链接地址以便访问相关资料。
URL
https://arxiv.org/abs/2507.02403
