arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.03444cs.CV
收藏

基于动态上下文对应网络的语义对齐

Dynamic Context Correspondence Network for Semantic Alignment

ShanghaiTech University(上海科技大学)

Shuaiyi Huang, Qiuyue Wang, Songyang Zhang, Shipeng Yan, Xuming He

摘要:

建立语义对应是计算机视觉中的核心问题,并且由于类内变化大和缺乏注释数据而仍然具有挑战性。在本文中,我们的目标是将全球语义背景下,以灵活的方式,以克服现有的工作,依赖于本地语义表示的局限性。为此,我们首先提出了一个上下文感知的语义表示,结合了空间布局的鲁棒匹配对当地的歧义。然后,我们开发了一种新的动态融合策略的基础上注意力机制编织的本地和上下文特征的优势,通过集成多个尺度的语义线索。我们通过设计一个端到端可学习的深度网络来实例化我们的策略,称为动态上下文对应网络(DCCNet)。为了训练网络,我们采用了多辅助任务损失,以提高我们的弱监督学习过程的效率。我们的方法在几个具有挑战性的数据集(包括PF-Pascal,PF-Willow和TSS)上实现了优于以前方法的性能,证明了其有效性和通用性。

英文摘要:

Establishing semantic correspondence is a core problem in computer vision and remains challenging due to large intra-class variations and lack of annotated data. In this paper, we aim to incorporate global semantic context in a flexible manner to overcome the limitations of prior work that relies on local semantic representations. To this end, we first propose a context-aware semantic representation that incorporates spatial layout for robust matching against local ambiguities. We then develop a novel dynamic fusion strategy based on attention mechanism to weave the advantages of both local and context features by integrating semantic cues from multiple scales. We instantiate our strategy by designing an end-to-end learnable deep network, named as Dynamic Context Correspondence Network (DCCNet). To train the network, we adopt a multi-auxiliary task loss to improve the efficiency of our weakly-supervised learning procedure. Our approach achieves superior or competitive performance over previous methods on several challenging datasets, including PF-Pascal, PF-Willow, and TSS, demonstrating its effectiveness and generality.

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。

↑