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 2102.01523cs.CV
收藏

方向卷积网络在图像识别中的应用

Orientation Convolutional Networks for Image Recognition

Shanghai University(上海大学)

Yalan Qin, Guorui Feng, Hanzhou Wu, Yanli Ren, Xinpeng Zhang

摘要:

深度卷积神经网络(DCNN)能够获得强大的图像表示能力,在图像识别领域引起了广泛的关注。然而,它们在建模方向转换方面受到内部机制的限制。在本文中,我们开发了方向卷积网络(OCN)的图像识别的基础上提出的地标Gabor滤波器(LGF)的学习表示的鲁棒性对方向的变化可以增强。通过用LGF调制卷积滤波器,OCN可以与任何现有的深度学习网络兼容。LGF充当通过选择$ p $ $ \left( \ll n\right) $代表性的Gabor滤波器作为andmark实现的Gabor滤波器组,并且将原始的Gabor滤波器表示为这些界标的稀疏线性组合。具体地说,基于矩阵分解框架,利用稀疏性和低秩约束的原始Gabor滤波器的局部和全局结构的灵活集成。通过低秩结构的传播,可以显著提高原Gabor滤波器组表示的稀疏性。多个基准测试的实验结果表明,与现有的最先进的方法相比,我们的方法对方向不太敏感,并且在精度和成本方面都具有更高的性能。此外,我们的OCN有很少的参数学习,可以显着降低训练网络的复杂性。

英文摘要:

Deep Convolutional Neural Networks (DCNNs) are capable of obtaining powerful image representations, which have attracted great attentions in image recognition. However, they are limited in modeling orientation transformation by the internal mechanism. In this paper, we develop Orientation Convolution Networks (OCNs) for image recognition based on the proposed Landmark Gabor Filters (LGFs) that the robustness of the learned representation against changed of orientation can be enhanced. By modulating the convolutional filter with LGFs, OCNs can be compatible with any existing deep learning networks. LGFs act as a Gabor filter bank achieved by selecting $ p $ $ \left( \ll n\right) $ representative Gabor filters as andmarks and express the original Gabor filters as sparse linear combinations of these landmarks. Specifically, based on a matrix factorization framework, a flexible integration for the local and the global structure of original Gabor filters by sparsity and low-rank constraints is utilized. With the propogation of the low-rank structure, the corresponding sparsity for representation of original Gabor filter bank can be significantly promoted. Experimental results over several benchmarks demonstrate that our method is less sensitive to the orientation and produce higher performance both in accuracy and cost, compared with the existing state-of-art methods. Besides, our OCNs have few parameters to learn and can significantly reduce the complexity of training network.

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。

↑