Deep invariant networks with differentiable augmentation layers
- URL: http://arxiv.org/abs/2202.02142v2
- Date: Mon, 7 Feb 2022 20:55:20 GMT
- Title: Deep invariant networks with differentiable augmentation layers
- Authors: C\'edric Rommel, Thomas Moreau and Alexandre Gramfort
- Abstract summary: Methods for learning data augmentation policies require held-out data and are based on bilevel optimization problems.
We show that our approach is easier and faster to train than modern automatic data augmentation techniques.
- Score: 87.22033101185201
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Designing learning systems which are invariant to certain data
transformations is critical in machine learning. Practitioners can typically
enforce a desired invariance on the trained model through the choice of a
network architecture, e.g. using convolutions for translations, or using data
augmentation. Yet, enforcing true invariance in the network can be difficult,
and data invariances are not always known a piori. State-of-the-art methods for
learning data augmentation policies require held-out data and are based on
bilevel optimization problems, which are complex to solve and often
computationally demanding. In this work we investigate new ways of learning
invariances only from the training data. Using learnable augmentation layers
built directly in the network, we demonstrate that our method is very
versatile. It can incorporate any type of differentiable augmentation and be
applied to a broad class of learning problems beyond computer vision. We
provide empirical evidence showing that our approach is easier and faster to
train than modern automatic data augmentation techniques based on bilevel
optimization, while achieving comparable results. Experiments show that while
the invariances transferred to a model through automatic data augmentation are
limited by the model expressivity, the invariance yielded by our approach is
insensitive to it by design.
Related papers
- Adaptive Parameterization of Deep Learning Models for Federated Learning [85.82002651944254]
Federated Learning offers a way to train deep neural networks in a distributed fashion.
It incurs a communication overhead as the model parameters or gradients need to be exchanged regularly during training.
In this paper, we propose to utilise parallel Adapters for Federated Learning.
arXiv Detail & Related papers (2023-02-06T17:30:33Z) - Automatic Data Augmentation via Invariance-Constrained Learning [94.27081585149836]
Underlying data structures are often exploited to improve the solution of learning tasks.
Data augmentation induces these symmetries during training by applying multiple transformations to the input data.
This work tackles these issues by automatically adapting the data augmentation while solving the learning task.
arXiv Detail & Related papers (2022-09-29T18:11:01Z) - A Simple Strategy to Provable Invariance via Orbit Mapping [14.127786615513978]
We propose a method to make network architectures provably invariant with respect to group actions.
In a nutshell, we intend to 'undo' any possible transformation before feeding the data into the actual network.
arXiv Detail & Related papers (2022-09-24T03:40:42Z) - HyperInvariances: Amortizing Invariance Learning [10.189246340672245]
Invariance learning is expensive and data intensive for popular neural architectures.
We introduce the notion of amortizing invariance learning.
This framework can identify appropriate invariances in different downstream tasks and lead to comparable or better test performance.
arXiv Detail & Related papers (2022-07-17T21:40:37Z) - Invariance Learning in Deep Neural Networks with Differentiable Laplace
Approximations [76.82124752950148]
We develop a convenient gradient-based method for selecting the data augmentation.
We use a differentiable Kronecker-factored Laplace approximation to the marginal likelihood as our objective.
arXiv Detail & Related papers (2022-02-22T02:51:11Z) - CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG
Signals [92.60744099084157]
We propose differentiable data augmentation amenable to gradient-based learning.
We demonstrate the relevance of our approach on the clinically relevant sleep staging classification task.
arXiv Detail & Related papers (2021-06-25T15:28:48Z) - Category-Learning with Context-Augmented Autoencoder [63.05016513788047]
Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning.
We propose a novel method of using data augmentations when training autoencoders.
We train a Variational Autoencoder in such a way, that it makes transformation outcome predictable by auxiliary network.
arXiv Detail & Related papers (2020-10-10T14:04:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.