当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
SML: Semantic meta-learning for few-shot semantic segmentation☆
Pattern Recognition Letters ( IF 5.1 ) Pub Date : 2021-04-20 , DOI: 10.1016/j.patrec.2021.03.036
Ayyappa Kumar Pambala , Titir Dutta , Soma Biswas

The significant amount of training data required for training Convolutional Neural Networks has become a bottleneck for applications like semantic segmentation. Few-shot semantic segmentation algorithms address this problem, with an aim to achieve good performance in the low-data regime, with few annotated training images. Recent approaches based on class-prototypes computed from available training data have achieved immense success for this task. In this work, we propose a novel meta-learning framework, Semantic Meta-Learning (SML), which incorporates class level semantic descriptions in the generated prototypes for this problem. In addition, we propose to use the well-established technique, ridge regression, to not only bring in the class-level semantic information, but also to effectively utilise the information available from multiple images present in the training data for prototype computation. This has a simple closed-form solution, and thus can be implemented easily and efficiently. Extensive experiments on the benchmark PASCAL-5i dataset under different experimental settings demonstrate the effectiveness of the proposed framework.



中文翻译:

SML:语义元学习,用于几次语义分割

训练卷积神经网络所需的大量训练数据已成为语义分割等应用程序的瓶颈。很少有语义分割算法解决了这个问题,目的是在低数据量的情况下获得良好的性能,并且带有很少的带注释的训练图像。基于从可用训练数据中计算出的类原型的最新方法,已经在这项任务上取得了巨大的成功。在这项工作中,我们提出了一种新颖的元学习框架,语义元学习(SML),该框架在生成的该问题的原型中合并了类级别的语义描述。另外,我们建议使用成熟的技术ridge回归,不仅引入类级语义信息,而且还可以有效地利用训练数据中存在的多个图像中的可用信息进行原型计算。这具有简单的封闭形式的解决方案,因此可以轻松有效地实现。在不同的实验设置下,对基准PASCAL-5i数据集进行的大量实验证明了所提出框架的有效性。

更新日期:2021-05-03
down
wechat
bug