The augmentation parameters matter to few-shot semantic segmentation since they directly affect the training outcome by feeding the networks with varying perturbated samples. However, searching optimal augmentation parameters for few-shot segmentation models without annotations is a challenge that current methods fail to address. In this paper, we first propose a framework to determine the ``optimal'' parameters without human annotations by solving a distribution-matching problem between the intra-instance and intra-class similarity distribution, with the intra-instance similarity describing the similarity between the original sample of a particular anatomy and its augmented ones and the intra-class similarity representing the similarity between the selected sample and the others in the same class. Extensive experiments demonstrate the superiority of our optimized augmentation in boosting few-shot segmentation models. We greatly improve the top competing method by 1.27\% and 1.11\% on Abd-MRI and Abd-CT datasets, respectively, and even achieve a significant improvement for SSL-ALP on the left kidney by 3.39\% on the Abd-CT dataset.

翻译：增强参数对少样本语义分割至关重要，因为它们通过向网络输入不同的扰动样本来直接影响训练结果。然而，在没有标注的情况下为少样本分割模型搜索最优增强参数，是当前方法未能解决的挑战。本文首次提出一个框架，通过求解实例内相似度与类内相似度分布之间的匹配问题，在无人工标注的情况下确定“最优”参数：其中实例内相似度描述特定解剖结构原始样本与其增强样本之间的相似性，类内相似度则表示选定样本与同一类别中其他样本之间的相似性。大量实验证明了我们所优化增强方法在提升少样本分割模型性能方面的优越性。我们在Abd-MRI和Abd-CT数据集上分别将最优竞争方法的性能提高了1.27%和1.11%，甚至在Abd-CT数据集的左肾脏分割任务上，对SSL-ALP方法实现了3.39%的显著提升。