Deep Rotation Equivariant Network

By Junying Li, Zichen Yang, Haifeng Liu, Deng Cai. 2017

61 citations recorded by the source corpus.

Recently, learning equivariant representations has attracted considerable research attention. Dieleman et al. introduce four operations which can be inserted into convolutional neural network to learn deep representations equivariant to rotation. However, feature maps should be copied and rotated four times in each layer in their approach, which causes much running time and memory overhead. In order to address this problem, we propose Deep Rotation Equivariant Network consisting of cycle layers, isotonic layers and decycle layers. Our proposed layers apply rotation transformation on filters rather than feature maps, achieving a speed up of more than 2 times with even less memory overhead. We evaluate DRENs on Rotated MNIST and CIFAR-10 datasets and demonstrate that it can improve the performance of state-of-the-art architectures.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Group Equivariant Stand-Alone Self-Attention For Vision (2020, background): “…to additional symmetries ranging from planar rotations (Dieleman et al., 2016; Marcos et al., 2017; Worrall et al., 2017; Weiler et al., 2018b; Li et al., 2018; Cheng et al., 2018; Hoogeboom et al., 2018; Bekkers et al., 2018; Veeling et al., 2018; Lenssen et al., 2018; Graham et al., 2020)…”
Tensor Field Networks: Rotation- and Translation-Equivariant Neural Networks for 3D Point Clouds (2018, background): “Other authors have investigated the problems of rotation equivariance in 2D, such as Zhou et al. [4], Gonzalez et al. [5], Li et al. [6].”
CubeNet: Equivariance to 3D Rotation and Translation (2018, background): “Recently there has been an explosion of interest into CNNs with predefined transformation equivariances, beyond translation [8, 50, 11, 29, 16, 42, 36, 14, 19, 31, 18, 22, 15, 55, 49, 26, 25, 48, 33, 28, 9].”
Attentive Group Equivariant Convolutional Networks (2020, background): “…translations (LeCun et al., 1989), planar rotations (Dieleman et al., 2016; Marcos et al., 2017; Worrall et al., 2017; Weiler et al., 2018; Li et al., 2018; Cheng et al., 2018; Bekkers et al., 2018; Lenssen et al., 2018; Smets et al., 2020), spherical rotations (Cohen et al., 2018;…”
Robustness of Rotation-Equivariant Networks to Adversarial Perturbations (2018, methodology): “Deep Rotation Equivariant Networks (Li et al., 2017) are also competitive on MNIST-rot and CIFAR-10, but must be equivalent to G-CNNs with the group p 4 , up to differences in the proposed architecture and learning procedure (Kondor & Trivedi, 2018).”
HexaConv (2018, background): “…or the feature maps followed and subsequent channel permutations to obtain equivariant (or invariant) CNNs (Cohen & Welling, 2016; Dieleman et al., 2016; Zhou et al., 2017; Li et al., 2017 To simplify the exposition, we assume there is only one input channel and one output channel; K = C = 1 .”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “Invariances [132], [134], [135], [137], [138], [139], [140] [133], [141], [142]”
Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data (2019, methodology): “…several approaches have emerged to extend equivariance to, e.g., planar rotations (Dieleman et al., 2016; Marcos et al., 2017; Weiler et al., 2018; Li et al., 2018), spherical rotations (Cohen et al., 2018; Worrall & Brostow, 2018; Cohen et al., 2019), scaling (Marcos et al., 2018; Worrall &…”