Pattern recognition (psychology)

Key (lock)

Meta learning (computer science)

Mathematics

Domain (mathematical analysis)

Psychotherapist

Contextual image classification

Image (mathematics)

Geodesy

Variety (cybernetics)

Machine learning

Mathematical analysis

Benchmark (surveying)

Artificial intelligence

Management

Psychology

Economics

Geography

Object detection

Computer science

Task (project management)

Generality

Computer security

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.

Meta-Learning to Detect Rare Objects