Attentive group equivariant convolutional networks

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

20 Downloads (Pure)


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.
Original languageEnglish
Title of host publicationProceedings of the 37th International Conference on Machine Learning [Online]
EditorsHal Daumé III, Aarti Singh
Number of pages12
Publication statusPublished - 2020
Event37th International Conference on Machine Learning, 13-18 July 2020, Virtual -
Duration: 13 Jul 202018 Jul 2020
Conference number: 37

Publication series

NameProceedings of Machine Learning Research


Conference37th International Conference on Machine Learning, 13-18 July 2020, Virtual


Dive into the research topics of 'Attentive group equivariant convolutional networks'. Together they form a unique fingerprint.

Cite this