发表机构
Jagiellonian University; Jagiellonian Center for Artificial Intelligence; NASK National Research Institute（雅盖隆大学; 雅盖隆人工智能中心; NASK国家研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
WildMatch提出一种弱监督方法，利用身份标签自适应预训练关键点匹配器，通过对比微调增强同身份对应并抑制异身份，提升野生动物再识别准确率。
AI 中文摘要
从相机陷阱图像中识别个体动物是一个实例检索问题，对于非侵入式野生动物监测至关重要：查询图像必须从已知动物的参考集中检索出正确的个体。这要求计算机视觉模型能够识别皮毛、皮肤或其他视觉标记中的独特局部模式。当前的方法要么将全局嵌入学习视为分类问题，需要每个个体的大量标注图像，同时很大程度上忽略局部证据；要么应用现成的、领域无关的图像匹配器。尽管这类匹配器在大型多样化的图像集上进行了预训练，但将其适应于野生动物图像具有挑战性，因为可用数据集较小且缺乏对应级别的标注。我们研究了仅使用身份标签对预训练关键点匹配器进行弱监督自适应，而无需关键点级别或几何对应真值。我们利用预训练匹配器挖掘信息丰富的图像对，从身份一致性中推导出弱正负监督，并对匹配网络进行对比微调，以增强同一身份对的对应关系并抑制不同身份对的对应关系。在开源野生动物再识别数据集上，我们的方法相比现成匹配器和最先进的局部-全局融合方法提高了准确性。在包含未见个体的开放世界协议下，它学习了一种可迁移的对应先验，而不是记忆训练身份。据我们所知，这是首次针对动物再识别的匹配器级别、身份监督自适应研究。我们的方法利用典型监测数据集中已有的身份标注，实现了图像匹配模型对野生动物领域的数据高效专业化。
英文摘要
Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wildlife monitoring: a query image must retrieve the correct individual from a reference set of known animals. This requires computer vision models to recognize distinctive local patterns in fur, skin, or other visual markings. Current approaches either learn global embeddings as a classification problem, requiring many labeled images per individual while largely ignoring local evidence, or apply off-the-shelf, domain-agnostic image matchers. Although such matchers are pretrained on large and diverse image collections, adapting them to wildlife imagery is challenging because available datasets are small and lack correspondence-level annotations. We study weakly supervised adaptation of a pretrained keypoint matcher using only identity labels, without keypoint-level or geometric correspondence ground truth. We mine informative image pairs with the pretrained matcher, derive weak positive and negative supervision from identity agreement, and contrastively fine-tune the matching network to strengthen correspondences for same-identity pairs and suppress them for different identities. Across open-source wildlife re-identification datasets, our approach improves accuracy over off-the-shelf matchers and a state-of-the-art local--global fusion method. Under an open-world protocol with held-out individuals, it learns a transferable correspondence prior rather than memorizing training identities. To our knowledge, this is the first study of matcher-level, identity-supervised adaptation for animal re-identification. Our method enables data-efficient specialization of image matching models to wildlife domains using identity annotations already available in typical monitoring datasets.
Comments15 pages, 7 figures, 3 tables. Project page: https://wildmatch.gmum.net
