Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data
This addresses the issue of inefficient equivariance in neural networks for computer vision tasks, offering a more parameter-efficient approach, though it is incremental as it builds on existing equivariant architectures.
The paper tackled the problem of conventional equivariant neural networks considering all possible transformations, even irrelevant ones, by proposing co-attentive equivariant neural networks that focus on co-occurring transformations in data. The result showed consistent outperformance over conventional rotation and rotation & reflection equivariant networks on rotated MNIST and CIFAR-10 datasets.
Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformations might never appear (e.g. an upright face with a horizontal nose), current equivariant architectures consider the set of all possible transformations in a transformation group when learning feature representations. Contrarily, the human visual system is able to attend to the set of relevant transformations occurring in the environment and utilizes this information to assist and improve object recognition. Based on this observation, we modify conventional equivariant feature mappings such that they are able to attend to the set of co-occurring transformations in data and generalize this notion to act on groups consisting of multiple symmetries. We show that our proposed co-attentive equivariant neural networks consistently outperform conventional rotation equivariant and rotation & reflection equivariant neural networks on rotated MNIST and CIFAR-10.