arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.05202cs.CV
收藏

典型的图神经网络

Representative Graph Neural Network

Huazhong University of Science & Technology(华中科技大学);The University of Adelaide(阿德莱德大学)

Changqian Yu, Yifan Liu, Changxin Gao, Chunhua Shen, Nong Sang

摘要:

非局部操作被广泛地用于建模远程依赖。然而,该操作中的冗余计算导致了过高的复杂性。在本文中,我们提出了一个代表图(RepGraph)层动态采样的一些代表性的功能,这大大减少了冗余。我们的RepGraph层不是从所有位置传播消息,而是仅用几个代表性节点计算一个节点的响应。代表节点的位置来自学习的空间偏移矩阵。RepGraph层可以灵活地集成到许多可视化架构中,并与其他操作相结合。通过应用语义分割,没有任何花哨的东西,我们的RepGraph网络可以在三个具有挑战性的基准上与最先进的方法竞争或表现良好:ADE 20 K,Cityscapes和PASCAL-Context数据集。在目标检测任务中,与非局部操作相比,我们的RepGraph层还可以提高COCO数据集上的性能。代码可在https://git.io/RepGraph上获得。

英文摘要:

Non-local operation is widely explored to model the long-range dependencies. However, the redundant computation in this operation leads to a prohibitive complexity. In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy. Instead of propagating the messages from all positions, our RepGraph layer computes the response of one node merely with a few representative nodes. The locations of representative nodes come from a learned spatial offset matrix. The RepGraph layer is flexible to integrate into many visual architectures and combine with other operations. With the application of semantic segmentation, without any bells and whistles, our RepGraph network can compete or perform favourably against the state-of-the-art methods on three challenging benchmarks: ADE20K, Cityscapes, and PASCAL-Context datasets. In the task of object detection, our RepGraph layer can also improve the performance on the COCO dataset compared to the non-local operation. Code is available at https://git.io/RepGraph.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑