We tackle a novel few-shot learning challenge, few-shot semantic edge detection, aiming to localize boundaries of novel categories using only a few labeled samples. Reliable boundary information has been shown to boost the performance of semantic segmentation and localization, while also playing a key role in its own right in object reconstruction, image generation and medical imaging. However, existing semantic edge detection techniques require a large amount of labeled data to train a model. To overcome this limitation, we present Class-Agnostic Few-shot Edge detection Network (CAFENet) based on a meta-learning strategy. CAFENet employs a semantic segmentation module in small-scale to compensate for the lack of semantic information in edge labels. To effectively fuse the semantic information and low-level cues, CAFENet also utilizes an attention module which dynamically generates multi-scale attention map, as well as a novel regularization method that splits high-dimensional features into several low-dimensional features and conducts multiple metric learning. Since there are no existing datasets for few-shot semantic edge detection, we construct two new datasets, FSE-1000 and SBD5 i , and evaluate the performance of the proposed CAFENet on them. Extensive simulation results confirm that CAFENet achieves better performance compared to the baseline methods using fine-tuning or few-shot segmentation.