CAFENet: Class-Agnostic Few-Shot Edge Detection Network

Younghyun Park, Jun Seo, Jaekyun Moon

Keywords: Few-shot edge detection, Few-shot learning, Semantic edge detection

Abstract: 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. Few-shot semantic edge detection allows recovery of accurate boundaries with just a few examples. In this work, we present a Class-Agnostic Few-shot Edge detection Network (CAFENet) based on meta-learning strategy. CAFENet employs a semantic segmentation module in small-scale to compensate for lack of semantic information in edge labels. The predicted segmentation mask is used to generate an attention map to highlight the target object region, and make the decoder module concentrate on that region. We also propose a new regularization method based on multi-split matching. In meta-training, the metric-learning problem with high-dimensional vectors are divided into smaller subproblems with low-dimensional sub-vectors. Since there are no existing datasets for few-shot semantic edge detection, we construct two new datasets, FSE-1000 and SBD-5i, and evaluate the performance of the proposed CAFENet on them. Extensive simulation results confirm that the proposed CAFENet achieves better performance compared to the baseline methods using fine-tuning or few-shot segmentation.

One-sentence Summary: We introduce a novel few-shot learning setup, few-shot semantic edge detection, and propose a few-shot edge detector CAFENet . We also construct new datasets for few-shot edge detection and validate CAFENet.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=oFmpqmyO-B