arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.08991cs.CV
收藏

用于稠密预测的频域和空域联合学习

Joint Learning of Frequency and Spatial Domains for Dense Predictions

The Hong Kong Polytechnic University(香港理工大学);The University of Hong Kong(香港大学);The Hong Kong Polytechnic University Shenzhen Research Institute(香港理工大学深圳研究院)

Shaocheng Jia, Wei Yao

摘要:

目前的人工神经网络主要在空间域进行学习,而忽略了频域学习。然而,在频域中执行的学习过程可以比在空间域中执行的学习过程更有效。在本文中,我们充分探讨了频域学习,并提出了一个联合学习范式的频率和空间域。该范式可以充分利用频率学习和空间学习的优势;具体而言,频率和空间域学习可以分别有效地捕获全局和局部信息。对两个密集预测任务进行了详尽的实验,即,自监督深度估计和语义分割,表明所提出的联合学习范例可以1)在深度估计和语义分割任务中实现与现有技术方法的性能竞争的性能,即使没有预训练;以及2)与其他现有技术方法相比,显著减少了参数的数量,这为开发真实世界的应用提供了更多的机会。我们希望所提出的方法能够鼓励更多跨领域学习的研究。

英文摘要:

Current artificial neural networks mainly conduct the learning process in the spatial domain but neglect the frequency domain learning. However, the learning course performed in the frequency domain can be more efficient than that in the spatial domain. In this paper, we fully explore frequency domain learning and propose a joint learning paradigm of frequency and spatial domains. This paradigm can take full advantage of the preponderances of frequency learning and spatial learning; specifically, frequency and spatial domain learning can effectively capture global and local information, respectively. Exhaustive experiments on two dense prediction tasks, i.e., self-supervised depth estimation and semantic segmentation, demonstrate that the proposed joint learning paradigm can 1) achieve performance competitive to those of state-of-the-art methods in both depth estimation and semantic segmentation tasks, even without pretraining; and 2) significantly reduce the number of parameters compared to other state-of-the-art methods, which provides more chance to develop real-world applications. We hope that the proposed method can encourage more research in cross-domain learning.

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。

↑