提出无需重训练的野生动物开放集识别方法，通过特征与预测一致性的度量提升未知样本拒识能力。
Nearest-Class Mean and Logits Agreement for Wildlife Open-Set Recognition
- 基于最近类均值距离构建概率分布，与分类头输出的softmax概率比对一致性
- 在非洲和瑞典动物数据集上分别取得93.41和95.35的AUROC，性能稳定且排名前三
- 可直接应用于预训练模型，适合希望快速部署开放集识别的实践者
当前主流野生动物分类模型均在闭世界设定下训练，面对未知类别时仍表现过度自信。开放集识别（OSR）旨在对已知类别进行分类的同时拒绝未知样本。现有方法多需针对OSR重新训练预训练模型，存在成本高、适配难的问题。本文提出一种后处理OSR方法，通过度量模型特征与预测logit之间的一致性来判断样本归属。具体地，构建基于输入到最近类均值（NCM）距离的概率分布，并与logit空间中的softmax概率进行对比，评估二者一致性。该策略在两个数据集上均位列前三，表现稳定；在非洲动物和瑞典动物数据集上分别达到93.41和95.35的AUROC。代码已公开于https://github.com/Applied-Representation-Learning-Lab/OSR。
原文摘要 · Abstract (English)
Current state-of-the-art Wildlife classification models are trained under the closed world setting. When exposed to unknown classes, they remain overconfident in their predictions. Open-set Recognition (OSR) aims to classify known classes while rejecting unknown samples. Several OSR methods have been proposed to model the closed-set distribution by observing the feature, logit, or softmax probability space. A significant drawback of many existing approaches is the requirement to retrain the pre-trained classification model with the OSR-specific strategy. This study contributes a post-processing OSR method that measures the agreement between the models' features and predicted logits. We propose a probability distribution based on an input's distance to its Nearest Class Mean (NCM). The NCM-based distribution is then compared with the softmax probabilities from the logit space to measure agreement between the NCM and the classification head. Our proposed strategy ranks within the top three on two evaluated datasets, showing consistent performance across the two datasets. In contrast, current state-of-the-art methods excel on a single dataset. We achieve an AUROC of 93.41 and 95.35 for African and Swedish animals. The code can be found https://github.com/Applied-Representation-Learning-Lab/OSR.
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。