论文标题
物体意识到的几个语义分段
Objectness-Aware Few-Shot Semantic Segmentation
论文作者
论文摘要
很少有语义分割模型仅在几个带注释的示例中学习后，旨在细分图像。对他们来说，关键的挑战是如何避免过度拟合，因为有限的培训数据可用。尽管以前的工作通常限制了减轻过度拟合的整体模型能力，但这种阻碍了细分精度。我们演示了如何通过引入类不足的物体来提高整体模型能力以提高绩效，因此不容易过度拟合，以辅助使用特定于类的功能。广泛的实验证明了我们简单的方法为依赖不同数据加载程序和训练时间表（DENET，PFENET）以及不同骨干模型（Resnet-50，Resnet-50，Resnet-101和HRNETV2-W48）引入不同基础体系结构的简单方法。只有一个注释类别的一个注释示例，实验表明，我们的方法在Pascal-5i和Coco-20i上分别优于MIOU的最先进方法，至少高4.7％和1.5％。
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.
