Publications [#368018] of Xiuyuan Cheng

Papers Published

1. Zhu, W; Qiu, Q; Calderbank, R; Sapiro, G; Cheng, X, Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters, Journal of Machine Learning Research, vol. 23 (January, 2022)
   (last updated on 2024/04/19)

   Abstract:
   Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when dealing with multiscale inputs. We study, in this paper, a scaling-translation-equivariant (ST -equivariant) CNN with joint convolutions across the space and the scaling group, which is shown to be both sufficient and necessary to achieve equivariance for the regular representation of the scaling-translation group ST . To reduce the model complexity and computational burden, we decompose the convolutional filters under two pre-fixed separable bases and truncate the expansion to low-frequency components. A further benefit of the truncated filter expansion is the improved deformation robustness of the equivariant representation, a property which is theoretically analyzed and empirically verified. Numerical experiments demonstrate that the proposed scaling-translation-equivariant network with decomposed convolutional filters (ScDCFNet) achieves significantly improved performance in multiscale image classification and better interpretability than regular CNNs at a reduced model size.