October
2019
Meta-Learning to Detect Rare Objects
Authors:
Abstract:
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.
copied = false, 2000);
">
@conference{Wang-2019-121131,
author = {Y. Wang And D. Ramanan And M. Hebert},
title = {Meta-Learning to Detect Rare Objects},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2019},
month = {October},
pages = {9924 - 9933},
}
author = {Y. Wang And D. Ramanan And M. Hebert},
title = {Meta-Learning to Detect Rare Objects},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2019},
month = {October},
pages = {9924 - 9933},
}