MSI: Maximize Support-Set Information for Few-Shot Segmentation
MSI: Maximize Support-Set Information for Few-Shot Segmentation
复制标题
DOI：
10.1109/iccv51070.2023.01765
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Seonghyeon Moon;Samuel S. Sohn;Honglu Zhou;Sejong Yoon;V. Pavlovic;Muhammad Haris Khan;M. Kapadia
中科院分区：
文献类型：
--
作者：
Seonghyeon Moon;Samuel S. Sohn;Honglu Zhou;Sejong Yoon;V. Pavlovic;Muhammad Haris Khan;M. Kapadia
FSS(少镜头分割)的目的是利用少量的标记图像(支持集)来分割目标类。为了提取与目标类相关的信息，性能最好的FSS方法中的一种主要方法是使用支持掩码去除背景特征。我们观察到，通过限制支持掩码的这种特征删除在几种具有挑战性的FSS情况下引入了信息瓶颈，例如，对于小目标和/或不准确的目标边界。为此，我们提出了一种新的方法(MSI)，它通过利用两个互补的特征源来生成超相关图来最大化支持集信息。我们通过将其实例化为三种最新的和强大的FSS方法来验证我们方法的有效性。在几个公开可用的FSS基准测试上的实验结果表明，我们提出的方法一致地提高了性能，并导致了更快的收敛速度。我们的代码和经过培训的模型可在以下网址获得：https://github.com/moonsh/MSI-Maximize-Support-Set-Information
FSS (Few-shot segmentation) aims to segment a target class using a small number of labeled images (support set). To extract information relevant to the target class, a dominant approach in best performing FSS methods removes background features using a support mask. We observe that this feature excision through a limiting support mask introduces an information bottleneck in several challenging FSS cases, e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method (MSI), which maximizes the support-set information by exploiting two complementary sources of features to generate super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS methods. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves performance by visible margins and leads to faster convergence. Our code and trained models are available at: https://github.com/moonsh/MSI-Maximize-Support-Set-Information