Data Augmentation and Regularization for Learning Group Equivariance
In many machine learning tasks, known symmetries can be used as an inductive bias to improve model performance. In this paper, we consider learning group equivariance through training with data augmentation. We summarize results from a previous paper of our own, and extend the results to show that equivariance of the trained model can be achieved through training on augmented data in tandem with regularization.
Code (1)
Tasks
Data AugmentationInductive BiasSimilar Papers 제목 키워드 기반
Soft Equivariance Regularization for Invariant Self-Supervised Learning
Self-supervised learning (SSL) typically learns representations invariant to semantic-preserving augmentations. While effective for recognition, enforcing strong invariance can suppress transformation-dependent structure…
Self-Supervised LearningDiffeomorphism-Equivariant Neural Networks
Incorporating group symmetries via equivariance into neural networks has emerged as a robust approach for overcoming the efficiency and data demands of modern deep learning. While most existing approaches, such as group …
Image RegistrationData AugmentationAASAE: Augmentation-Augmented Stochastic Autoencoders
Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple vi…
Contrastive LearningData Augmentationimage-classificationImage Classification+1AAVAE: Augmentation-Augmented Variational Autoencoders
Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple vi…
Contrastive LearningData Augmentationimage-classificationImage Classification+1Ensembles provably learn equivariance through data augmentation
Recently, it was proved that group equivariance emerges in ensembles of neural networks as the result of full augmentation in the limit of infinitely wide neural networks (neural tangent kernel limit). In this paper, we …
Data Augmentation