论文标题
咖啡馆：类别不合时宜的几射线边缘检测网络
CAFENet: Class-Agnostic Few-Shot Edge Detection Network
论文作者
论文摘要
我们解决了一个新颖的几次学习挑战，我们称之为几乎没有的语义边缘检测，旨在仅使用几个标记的样本来定位新型类别的清晰界限。我们还基于元学习策略提出了一个不合时宜的几杆边缘检测网络（CAFENET）。 Cafenet采用小型语义分割模块，以弥补边缘标签中缺乏语义信息。预测的分割掩码用于生成注意图以突出目标对象区域，并使解码器模块集中在该区域上。我们还提出了一种基于多级匹配的新正规化方法。在元训练中，高维矢量的度量学习问题分为具有低维基媒介的小子问题。由于没有现有的数据集可用于几个射击语义边缘检测，因此我们构建了两个新数据集，即FSE-1000和SBD- $ 5^i $，并评估了它们在它们上的cafenet的性能。广泛的仿真结果证实了咖啡馆中采用的技术的性能。
We tackle a novel few-shot learning challenge, which we call few-shot semantic edge detection, aiming to localize crisp boundaries of novel categories using only a few labeled samples. We also 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 small subproblems with low-dimensional sub-vectors. Since there is no existing dataset for few-shot semantic edge detection, we construct two new datasets, FSE-1000 and SBD-$5^i$, and evaluate the performance of the proposed CAFENet on them. Extensive simulation results confirm the performance merits of the techniques adopted in CAFENet.
