Meta-Learning To Detect Rare Objects
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)(2019)
摘要
Few-shot learning, i.e., learning novel concepts from few examples, is fundamental to practical visual recognition systems. While most of existing work has focused on few-shot classification, we make a step towards few-shot object detection, a more challenging yet under-explored task. We develop a conceptually simple but powerful meta-learning based framework that simultaneously tackles few-shot classification and few-shot localization in a unified, coherent way. This framework leverages meta-level knowledge about "model parameter generation" from base classes with abundant data to facilitate the generation of a detector for novel classes. Our key insight is to disentangle the learning of category-agnostic and category-specific components in a CNN based detection model. In particular, we introduce a weight prediction meta-model that enables predicting the parameters of category-specific components from few examples. We systematically benchmark the performance of modern detectors in the small-sample size regime. Experiments in a variety of realistic scenarios, including within-domain, cross-domain, and long-tailed settings, demonstrate the effectiveness and generality of our approach under different notions of novel classes.
更多查看译文
关键词
few-shot learning,practical visual recognition systems,few-shot classification,few-shot object detection,few-shot localization,meta-level knowledge,model parameter generation,base classes,category-specific components,CNN based detection model,weight prediction meta-model,meta-learning based framework,rare object detection,category-agnostic components
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络