Improving the Sample-Complexity of Deep Classification Networks with Invariant Integration

• URL: http://arxiv.org/abs/2202.03967v1
• Date: Tue, 8 Feb 2022 16:16:11 GMT
• Title: Improving the Sample-Complexity of Deep Classification Networks with Invariant Integration
• Authors: Matthias Rath and Alexandru Paul Condurache
• Abstract summary: Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks. We propose a novel monomial selection algorithm based on pruning methods to allow an application to more complex problems. We demonstrate the improved sample complexity on the Rotated-MNIST, SVHN and CIFAR-10 datasets.
• Score: 77.99182201815763
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks. This makes them applicable to practically important use-cases where training data is scarce. Rather than being learned, this knowledge can be embedded by enforcing invariance to those transformations. Invariance can be imposed using group-equivariant convolutions followed by a pooling operation. For rotation-invariance, previous work investigated replacing the spatial pooling operation with invariant integration which explicitly constructs invariant representations. Invariant integration uses monomials which are selected using an iterative approach requiring expensive pre-training. We propose a novel monomial selection algorithm based on pruning methods to allow an application to more complex problems. Additionally, we replace monomials with different functions such as weighted sums, multi-layer perceptrons and self-attention, thereby streamlining the training of invariant-integration-based architectures. We demonstrate the improved sample complexity on the Rotated-MNIST, SVHN and CIFAR-10 datasets where rotation-invariant-integration-based Wide-ResNet architectures using monomials and weighted sums outperform the respective baselines in the limited sample regime. We achieve state-of-the-art results using full data on Rotated-MNIST and SVHN where rotation is a main source of intraclass variation. On STL-10 we outperform a standard and a rotation-equivariant convolutional neural network using pooling.

Related papers

• Universal Neural Functionals [67.80283995795985]
  A challenging problem in many modern machine learning tasks is to process weight-space features. Recent works have developed promising weight-space models that are equivariant to the permutation symmetries of simple feedforward networks. This work proposes an algorithm that automatically constructs permutation equivariant models for any weight space.
  arXiv  Detail & Related papers  (2024-02-07T20:12:27Z)
• Deep Neural Networks with Efficient Guaranteed Invariances [77.99182201815763]
  We address the problem of improving the performance and in particular the sample complexity of deep neural networks. Group-equivariant convolutions are a popular approach to obtain equivariant representations. We propose a multi-stream architecture, where each stream is invariant to a different transformation.
  arXiv  Detail & Related papers  (2023-03-02T20:44:45Z)
• Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need? [80.86819657126041]
  We show that transformation-invariant and distance-preserving initial representations are sufficient to achieve transformation invariance. Specifically, we realize transformation-invariant and distance-preserving initial point representations by modifying multi-dimensional scaling. We prove that TinvNN can strictly guarantee transformation invariance, being general and flexible enough to be combined with the existing neural networks.
  arXiv  Detail & Related papers  (2021-12-23T03:52:33Z)
• Implicit Equivariance in Convolutional Networks [1.911678487931003]
  Implicitly Equivariant Networks (IEN) induce equivariant in the different layers of a standard CNN model. We show IEN outperforms the state-of-the-art rotation equivariant tracking method while providing faster inference speed.
  arXiv  Detail & Related papers  (2021-11-28T14:44:17Z)
• Frame Averaging for Invariant and Equivariant Network Design [50.87023773850824]
  We introduce Frame Averaging (FA), a framework for adapting known (backbone) architectures to become invariant or equivariant to new symmetry types. We show that FA-based models have maximal expressive power in a broad setting. We propose a new class of universal Graph Neural Networks (GNNs), universal Euclidean motion invariant point cloud networks, and Euclidean motion invariant Message Passing (MP) GNNs.
  arXiv  Detail & Related papers  (2021-10-07T11:05:23Z)
• Training or Architecture? How to Incorporate Invariance in Neural Networks [14.162739081163444]
  We propose a method for provably invariant network architectures with respect to group actions. In a nutshell, we intend to 'undo' any possible transformation before feeding the data into the actual network. We analyze properties of such approaches, extend them to equivariant networks, and demonstrate their advantages in terms of robustness as well as computational efficiency in several numerical examples.
  arXiv  Detail & Related papers  (2021-06-18T10:31:00Z)
• Exploiting Invariance in Training Deep Neural Networks [4.169130102668252]
  Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains well with an initial learning rate 1.0, and easily generalizes to different tasks. Tested on ImageNet, MS COCO, and Cityscapes datasets, our proposed technique requires fewer iterations to train, surpasses all baselines by a large margin, seamlessly works on both small and large batch size training, and applies to different computer vision tasks of image classification, object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2021-03-30T19:18:31Z)
• Learnable Gabor modulated complex-valued networks for orientation robustness [4.024850952459758]
  Learnable Gabor Convolutional Networks (LGCNs) are parameter-efficient and offer increased model complexity. We investigate the robustness of complex valued convolutional weights with learned Gabor filters to enable orientation transformations.
  arXiv  Detail & Related papers  (2020-11-23T21:22:27Z)
• Invariant Integration in Deep Convolutional Feature Space [77.99182201815763]
  We show how to incorporate prior knowledge to a deep neural network architecture in a principled manner. We report state-of-the-art performance on the Rotated-MNIST dataset.
  arXiv  Detail & Related papers  (2020-04-20T09:45:43Z)

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.