Latent Equivariant Operators for Robust Object Recognition: Promises and Challenges

Minh T. Dinh, Stephane Deny

Track: tiny paper (up to 4 pages)

Keywords: Equivariance Learning, Out-of-domain Generalization, Group Theory

Abstract: Despite the successes of deep learning in computer vision, difficulties persist in recognizing objects that have undergone group-symmetric transformations rarely seen during training$\textemdash$for example objects seen in unusual poses, scales, positions, or combinations thereof. Equivariant neural networks are a solution to the problem of generalizing across symmetric transformations, but require knowledge of transformations *a priori*. An alternative family of architectures proposes to *learn equivariant operators* in a latent space, from *examples* of symmetric transformations. Here, using simple datasets of rotated and translated noisy MNIST, we illustrate how such architectures can successfully be harnessed for out-of-distribution classification, thus overcoming the limitations of both traditional and equivariant networks. While conceptually enticing, we discuss challenges ahead on the path of scaling these architectures to more complex datasets. Our code is available at https://github.com/BRAIN-Aalto/equivariant_operator.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 80