Few-shot semantic segmentation models aim to segment images after learning from only a few annotated examples. A key challenge for them is how to avoid overfitting because limited training data is available. While prior works usually limited the overall model capacity to alleviate overfitting, this hampers segmentation accuracy. We demonstrate how to increase overall model capacity to achieve improved performance, by introducing objectness, which is class-agnostic and so not prone to overfitting, for complementary use with class-specific features. Extensive experiments demonstrate the versatility of our simple approach of introducing objectness for different base architectures that rely on different data loaders and training schedules (DENet, PFENet) as well as with different backbone models (ResNet-50, ResNet-101 and HRNetV2-W48). Given only one annotated example of an unseen category, experiments show that our method outperforms state-of-art methods with respect to mIoU by at least 4.7% and 1.5% on PASCAL-5i and COCO-20i respectively.
翻译:仅从几个附加说明的例子中学习了少量的语义分解模型,这些模型的目的是在仅仅从几个附加说明的例子中了解图像的部位。对于它们来说,一个关键的挑战是如何避免由于有限的培训数据而过度装配。虽然以前的工作通常限制了缓解过度装配的总体模型能力,但这妨碍了分解的准确性。我们展示了如何提高总体模型能力,以便通过引入目标性来提高性能,这种目标性是等级不可知的,因此不易过度装配,以便与特定类别的特点相辅相成。 广泛的实验表明,我们采用简单方法为不同的基础结构(Denet, PFENet)以及不同的主干模型(ResNet-50, ResNet-101 和 HRNetV2-W48)引入物体性能的多功能性(ResNet-50, ResNet-101 和 HRNet-V2-W48 ) 。我们仅举了一个说明性的例子,表明,我们的方法在MIOU方面至少比PASAL-5i和CO-20i高出4.7%和1.5%。