Scale-Equivariant Steerable Networks
The effectiveness of Convolutional Neural Networks (CNNs) has been substantially attributed to their built-in property of translation equivariance. However, CNNs do not have embedded mechanisms to handle other types of transformations. In this work, we pay attention to scale changes, which regularly appear in various tasks due to the changing distances between the objects and the camera. First, we introduce the general theory for building scale-equivariant convolutional networks with steerable filters. We develop scale-convolution and generalize other common blocks to be scale-equivariant. We demonstrate the computational efficiency and numerical stability of the proposed method. We compare the proposed models to the previously developed methods for scale equivariance and local scale invariance. We demonstrate state-of-the-art results on MNIST-scale dataset and on STL-10 dataset in the supervised learning setting.
Code (1)
Tasks
Computational EfficiencyImage ClassificationTranslationSimilar Papers 제목 키워드 기반
Geometric and Physical Quantities Improve E(3) Equivariant Message Passing
Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that ge…
Graph Property PredictionGeneral E(2)-Equivariant Steerable CNNs
The big empirical success of group equivariant networks has led in recent years to the sprouting of a great variety of equivariant network architectures. A particular focus has thereby been on rotation and reflection equ…
Rotated MNIST3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
We present a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and equivariant convolutions to map between such…
General ClassificationGeneral $E(2)$-Equivariant Steerable CNNs
The big empirical success of group equivariant networks has led in recent years to the sprouting of a great variety of equivariant network architectures. A particular focus has thereby been on rotation and reflection equ…
Image ClassificationOn the Implicit Bias of Linear Equivariant Steerable Networks
We study the implicit bias of gradient flow on linear equivariant steerable networks in group-invariant binary classification. Our findings reveal that the parameterized predictor converges in direction to the unique gro…
Binary ClassificationData Augmentation