Equivariance-aware Architectural Optimization of Neural Networks
Incorporating equivariance to symmetry groups as a constraint during neural network training can improve performance and generalization for tasks exhibiting those symmetries, but such symmetries are often not perfectly nor explicitly present. This motivates algorithmically optimizing the architectural constraints imposed by equivariance. We propose the equivariance relaxation morphism, which preserves functionality while reparameterizing a group equivariant layer to operate with equivariance constraints on a subgroup, as well as the [G]-mixed equivariant layer, which mixes layers constrained to different groups to enable within-layer equivariance optimization. We further present evolutionary and differentiable neural architecture search (NAS) algorithms that utilize these mechanisms respectively for equivariance-aware architectural optimization. Experiments across a variety of datasets show the benefit of dynamically constrained equivariance to find effective architectures with approximate equivariance.
Code (0)
등록된 구현이 없습니다.
Tasks
Neural Architecture SearchSimilar Papers 제목 키워드 기반
EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks
Learning self-supervised representations that are invariant and equivariant to transformations is crucial for advancing beyond traditional visual classification tasks. However, many methods rely on predictor architecture…
Pose EstimationThe Lie Derivative for Measuring Learned Equivariance
Equivariance guarantees that a model's predictions capture key symmetries in data. When an image is translated or rotated, an equivariant model's representation of that image will translate or rotate accordingly. The suc…
Shift Variance in Scene Text Detection
Theory of convolutional neural networks suggests the property of shift equivariance, i.e., that a shifted input causes an equally shifted output. In practice, however, this is not always the case. This poses a great prob…
Scene Text DetectionText DetectionUncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
Accurate image registration is essential in many medical imaging applications, yet most deep registration networks provide little indication of when or where their predictions are unreliable. Existing uncertainty estimat…
Medical Image RegistrationEqvAfford: SE(3) Equivariance for Point-Level Affordance Learning
Humans perceive and interact with the world with the awareness of equivariance, facilitating us in manipulating different objects in diverse poses. For robotic manipulation, such equivariance also exists in many scenario…