Rotational 3D Texture Classification Using Group Equivariant CNNs

Convolutional Neural Networks (CNNs) traditionally encode translation equivariance via the convolution operation. Generalization to other transformations has recently received attraction to encode the knowledge of the data geometry in group convolution operations. Equivariance to rotation is particularly important for 3D image analysis due to the large diversity of possible pattern orientations. 3D texture is a particularly important cue for the analysis of medical images such as CT and MRI scans as it describes different types of tissues and lesions. In this paper, we evaluate the use of 3D group equivariant CNNs accounting for the simplified group of right-angle rotations to classify 3D synthetic textures from a publicly available dataset. The results validate the importance of rotation equivariance in a controlled setup and yet motivate the use of a finer coverage of orientations in order to obtain equivariance to realistic rotations present in 3D textures.

[1]  Gabriel J. Brostow,et al.  CubeNet: Equivariance to 3D Rotation and Translation , 2018, ECCV.

[2]  Kristin J. Dana,et al.  Deep TEN: Texture Encoding Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Iasonas Kokkinos,et al.  Deep Filter Banks for Texture Recognition, Description, and Segmentation , 2015, International Journal of Computer Vision.

[4]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[5]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[6]  Michael Unser,et al.  Rotation Invariance and Directional Sensitivity: Spherical Harmonics versus Radiomics Features , 2018, MLMI@MICCAI.

[7]  Maurice Weiler,et al.  Learning Steerable Filters for Rotation Equivariant CNNs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[8]  Simona Maggio,et al.  Robustness of Rotation-Equivariant Networks to Adversarial Perturbations , 2018, ArXiv.

[9]  Stephan J. Garbin,et al.  Harmonic Networks: Deep Translation and Rotation Equivariance , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Max Welling,et al.  Steerable CNNs , 2016, ICLR.

[12]  Max Welling,et al.  3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data , 2018, NeurIPS.

[13]  Taco Cohen,et al.  3D G-CNNs for Pulmonary Nodule Detection , 2018, ArXiv.

[14]  Paul F. Whelan,et al.  Using filter banks in Convolutional Neural Networks for texture classification , 2016, Pattern Recognit. Lett..

[15]  Max Welling,et al.  Group Equivariant Convolutional Networks , 2016, ICML.