Skip to yearly menu bar Skip to main content


Attentive Group Equivariant Convolutional Networks

David Romero · Erik Bekkers · Jakub Tomczak · Mark Hoogendoorn

Keywords: [ Architectures ] [ Computer Vision ] [ Deep Learning Theory ] [ Other ] [ Deep Learning - Theory ]


Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e.g., relative positions and poses). In this paper, we present attentive group equivariant convolutions, a generalization of the group convolution, in which attention is applied during the course of convolution to accentuate meaningful symmetry combinations and suppress non-plausible, misleading ones. We indicate that prior work on visual attention can be described as special cases of our proposed framework and show empirically that our attentive group equivariant convolutional networks consistently outperform conventional group convolutional networks on benchmark image datasets. Simultaneously, we provide interpretability to the learned concepts through the visualization of equivariant attention maps.

Chat is not available.