用原型相似度提升模型对未知物体的识别能力，效果显著。
Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity
- 通过类别原型特征相似度判断输入是否为未知物体
- 在Pascal VOC上检测MS-COCO的未知物体时误报率大幅降低
- 提出新评估方案，更合理衡量未知物体检测性能
在有限类别样本上训练的神经网络常会错误预测分布外（OOD）物体。我们发现同类别特征在特征空间中更聚集，不同类别则更分散。基于此，提出使用原型相似度进行OOD检测。借鉴少样本学习中的原型特征，设计新型检测网络Proto-OOD：利用对比损失增强类别原型表征，并通过计算输入特征与各类别原型的相似度来识别OOD数据。训练时，通过负向嵌入生成器合成OOD样本以训练相似度模块。在以Pascal VOC为内分布、MS-COCO为分布外数据集的设定下，Proto-OOD显著降低误报率（FPR）。针对现有评估指标局限性，提出更合理的评估协议。代码将开源。
原文摘要 · Abstract (English)
Neural networks that are trained on limited category samples often mispredict out-of-distribution (OOD) objects. We observe that features of the same category are more tightly clustered in feature space, while those of different categories are more dispersed. Based on this, we propose using prototype similarity for OOD detection. Drawing on widely used prototype features in few-shot learning, we introduce a novel OOD detection network structure (Proto-OOD). Proto-OOD enhances the representativeness of category prototypes using contrastive loss and detects OOD data by evaluating the similarity between input features and category prototypes. During training, Proto-OOD generates OOD samples for training the similarity module with a negative embedding generator. When Pascal VOC are used as the in-distribution dataset and MS-COCO as the OOD dataset, Proto-OOD significantly reduces the FPR (false positive rate). Moreover, considering the limitations of existing evaluation metrics, we propose a more reasonable evaluation protocol. The code will be released.
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。