论文标题
Biopt：BI级优化，用于几次分割
BiOpt: Bi-Level Optimization for Few-Shot Segmentation
论文作者
论文摘要
几乎没有射击分段是一项具有挑战性的任务，旨在将新类的对象细分给定稀缺的支持图像。在归纳环境中，现有的基于原型的方法着重于从支持图像中提取原型。但是，他们无法利用查询图像的语义信息。在本文中，我们提出了双层优化（BIOPT），该优化成功地从电感设置下从查询图像中计算了类原型。 Biopt的学习过程分解为两个嵌套环：内环和外循环。在每个任务上，内部循环旨在从查询图像中学习优化的原型。进行初始步骤是为了完全利用支持和查询功能的知识，以便将合理的初始化原型纳入内部循环。外循环旨在学习跨不同任务的歧视性嵌入空间。在两个基准上进行的广泛实验验证了我们提出的Biopt算法的优越性。特别是，我们始终在5次Pascal-$ 5^i $和1-Shot Coco- $ 20^i $上实现最先进的性能。
Few-shot segmentation is a challenging task that aims to segment objects of new classes given scarce support images. In the inductive setting, existing prototype-based methods focus on extracting prototypes from the support images; however, they fail to utilize semantic information of the query images. In this paper, we propose Bi-level Optimization (BiOpt), which succeeds to compute class prototypes from the query images under inductive setting. The learning procedure of BiOpt is decomposed into two nested loops: inner and outer loop. On each task, the inner loop aims to learn optimized prototypes from the query images. An init step is conducted to fully exploit knowledge from both support and query features, so as to give reasonable initialized prototypes into the inner loop. The outer loop aims to learn a discriminative embedding space across different tasks. Extensive experiments on two benchmarks verify the superiority of our proposed BiOpt algorithm. In particular, we consistently achieve the state-of-the-art performance on 5-shot PASCAL-$5^i$ and 1-shot COCO-$20^i$.
