论文标题
使用粗制监督改善几乎没有零件的细分
Improving Few-Shot Part Segmentation using Coarse Supervision
论文作者
论文摘要
在培训深层网络中进行部分分割的重要瓶颈是获得详细注释的成本。我们提出了一个框架，以利用粗糙标签，例如图形地面面具和关键点位置，这些位置容易用于某些类别以改善部分分割模型。一个关键的挑战是，这些注释是针对不同的任务和不同的标签样式收集的，并且不能轻易地映射到零件标签上。为此，我们建议共同学习标签样式与部分分割模型之间的依赖关系，从而使我们能够利用来自不同标签的监督。为了评估我们的方法，我们在Caltech-UCSD鸟类和OID飞机数据集上开发了基准。我们的方法优于基于多任务学习，半监督学习和竞争方法的基准，这些方法依赖于手动设计的损失功能，以利用稀疏的supervision。
A significant bottleneck in training deep networks for part segmentation is the cost of obtaining detailed annotations. We propose a framework to exploit coarse labels such as figure-ground masks and keypoint locations that are readily available for some categories to improve part segmentation models. A key challenge is that these annotations were collected for different tasks and with different labeling styles and cannot be readily mapped to the part labels. To this end, we propose to jointly learn the dependencies between labeling styles and the part segmentation model, allowing us to utilize supervision from diverse labels. To evaluate our approach we develop a benchmark on the Caltech-UCSD birds and OID Aircraft dataset. Our approach outperforms baselines based on multi-task learning, semi-supervised learning, and competitive methods relying on loss functions manually designed to exploit sparse-supervision.
