MSI: Maximize Support-Set Information for Few-Shot Segmentation

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.

少样本分割（Few-shot Segmentation）旨在通过少量带标注图像（支持集，support set）完成目标类别的分割任务。为提取与目标类别相关的有效信息，当前性能优异的少样本分割（FSS）方法多采用主流技术方案：借助支持掩码（support mask）剔除背景特征。我们观察到，在若干极具挑战性的少样本分割场景中，这种依托受限支持掩码的特征剔除操作会引入信息瓶颈，例如针对小目标或目标边界不准确的场景。