提升非洲五霸动物异常检测，让模型更敢说‘不知道’。
Improving Wildlife Out-of-Distribution Detection: Africas Big Five
- 用最近类均值法结合预训练特征，增强模型对未知物种的识别能力。
- 在三个关键指标上分别提升2%、4%和22%，优于现有最佳方法。
- 适合野生动物监测、冲突预警等实际场景应用。
缓解人兽冲突依赖于识别可能引发冲突的个体，如非洲五霸动物。计算机视觉为此提供了解决方案，但环境常包含多种物种。当前最先进的动物分类模型基于封闭世界假设，面对未知类别时仍过度自信。本研究聚焦野生动物的分布外（OOD）检测，特别针对非洲五霸。选取参数化最近类均值（NCM）与非参数对比学习作为基线，利用主流分类编码器的预训练和投影特征。此外，对比了文献中多种常见OOD方法。结果表明，基于特征的方法在不同分类阈值下表现出更强泛化能力；具体而言，使用ImageNet预训练特征的NCM，在AUPR-IN、AUPR-OUT和AUTC指标上分别比最优的OOD方法提升2%、4%和22%。代码已公开于https://github.com/pxpana/BIG5OOD。
原文摘要 · Abstract (English)
Mitigating human-wildlife conflict seeks to resolve unwanted encounters between these parties. Computer Vision provides a solution to identifying individuals that might escalate into conflict, such as members of the Big Five African animals. However, environments often contain several varied species. The current state-of-the-art animal classification models are trained under a closed-world assumption. They almost always remain overconfident in their predictions even when presented with unknown classes. This study investigates out-of-distribution (OOD) detection of wildlife, specifically the Big Five. To this end, we select a parametric Nearest Class Mean (NCM) and a non-parametric contrastive learning approach as baselines to take advantage of pretrained and projected features from popular classification encoders. Moreover, we compare our baselines to various common OOD methods in the literature. The results show feature-based methods reflect stronger generalisation capability across varying classification thresholds. Specifically, NCM with ImageNet pre-trained features achieves a 2%, 4% and 22% improvement on AUPR-IN, AUPR-OUT and AUTC over the best OOD methods, respectively. The code can be found here https://github.com/pxpana/BIG5OOD
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。