论文标题
MSANET：多相似性和注意力指导，以增加几分片段
MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
论文作者
论文摘要
很少有射击分段旨在仅给出少数标记的样品，将看不见的级对象细分。原型学习，支持功能通过平均全局和局部对象信息产生单个原型，在FSS中已广泛使用。但是，仅利用原型向量可能不足以代表所有训练数据的功能。为了提取丰富的特征并做出更精确的预测，我们提出了一个多相似性和注意力网络（MSANET），包括两个新型模块，一个多相似性模块和一个注意模块。多相似模块利用了支持图像和查询图像的多个特征图以估算准确的语义关系。注意模块指示网络专注于相关的信息。该网络已在标准FSS数据集，Pascal-5i 1-Shot，Pascal-5i 5-shot，Coco-20i 1-Shot和CoCo-20i 5-Shot上测试。具有RESNET-101骨架的MSANET分别达到了所有4基准数据集的最先进性能，其平均值超过联合（MIOU），分别为69.13％，73.99％，51.09％，56.80％。代码可在https://github.com/aivresearch/msanet上找到
Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. Prototype learning, where the support feature yields a singleor several prototypes by averaging global and local object information, has been widely used in FSS. However, utilizing only prototype vectors may be insufficient to represent the features for all training data. To extract abundant features and make more precise predictions, we propose a Multi-Similarity and Attention Network (MSANet) including two novel modules, a multi-similarity module and an attention module. The multi-similarity module exploits multiple feature-maps of support images and query images to estimate accurate semantic relationships. The attention module instructs the network to concentrate on class-relevant information. The network is tested on standard FSS datasets, PASCAL-5i 1-shot, PASCAL-5i 5-shot, COCO-20i 1-shot, and COCO-20i 5-shot. The MSANet with the backbone of ResNet-101 achieves the state-of-the-art performance for all 4-benchmark datasets with mean intersection over union (mIoU) of 69.13%, 73.99%, 51.09%, 56.80%, respectively. Code is available at https://github.com/AIVResearch/MSANet
