Implicit Equivariance in Convolutional Networks

• URL: http://arxiv.org/abs/2111.14157v1
• Date: Sun, 28 Nov 2021 14:44:17 GMT
• Title: Implicit Equivariance in Convolutional Networks
• Authors: Naman Khetan, Tushar Arora, Samee Ur Rehman, Deepak K. Gupta
• Abstract summary: 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.
• Score: 1.911678487931003
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Convolutional Neural Networks(CNN) are inherently equivariant under translations, however, they do not have an equivalent embedded mechanism to handle other transformations such as rotations and change in scale. Several approaches exist that make CNNs equivariant under other transformation groups by design. Among these, steerable CNNs have been especially effective. However, these approaches require redesigning standard networks with filters mapped from combinations of predefined basis involving complex analytical functions. We experimentally demonstrate that these restrictions in the choice of basis can lead to model weights that are sub-optimal for the primary deep learning task (e.g. classification). Moreover, such hard-baked explicit formulations make it difficult to design composite networks comprising heterogeneous feature groups. To circumvent such issues, we propose Implicitly Equivariant Networks (IEN) which induce equivariance in the different layers of a standard CNN model by optimizing a multi-objective loss function that combines the primary loss with an equivariance loss term. Through experiments with VGG and ResNet models on Rot-MNIST , Rot-TinyImageNet, Scale-MNIST and STL-10 datasets, we show that IEN, even with its simple formulation, performs better than steerable networks. Also, IEN facilitates construction of heterogeneous filter groups allowing reduction in number of channels in CNNs by a factor of over 30% while maintaining performance on par with baselines. The efficacy of IEN is further validated on the hard problem of visual object tracking. We show that IEN outperforms the state-of-the-art rotation equivariant tracking method while providing faster inference speed.

Related papers

• SO(2) and O(2) Equivariance in Image Recognition with Bessel-Convolutional Neural Networks [63.24965775030674]
  This work presents the development of Bessel-convolutional neural networks (B-CNNs) B-CNNs exploit a particular decomposition based on Bessel functions to modify the key operation between images and filters. Study is carried out to assess the performances of B-CNNs compared to other methods.
  arXiv  Detail & Related papers  (2023-04-18T18:06:35Z)
• 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)
• Equivariance versus Augmentation for Spherical Images [0.7388859384645262]
  We analyze the role of rotational equivariance in convolutional neural networks (CNNs) applied to spherical images. We compare the performance of the group equivariant networks known as S2CNNs and standard non-equivariant CNNs trained with an increasing amount of data augmentation.
  arXiv  Detail & Related papers  (2022-02-08T16:49:30Z)
• Improving the Sample-Complexity of Deep Classification Networks with Invariant Integration [77.99182201815763]
  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.
  arXiv  Detail & Related papers  (2022-02-08T16:16:11Z)
• 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)
• 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)
• Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods [8.660429288575367]
  We investigate how diffusion and variational models achieve rotation invariance and transfer these ideas to neural networks. We propose activation functions which couple network channels by combining information from several oriented filters. Our findings help to translate diffusion and variational models into mathematically well-grained network architectures, and provide novel concepts for model-based CNN design.
  arXiv  Detail & Related papers  (2021-08-31T17:34:40Z)
• Group Equivariant Neural Architecture Search via Group Decomposition and Reinforcement Learning [17.291131923335918]
  We prove a new group-theoretic result in the context of equivariant neural networks. We also design an algorithm to construct equivariant networks that significantly improves computational complexity. We use deep Q-learning to search for group equivariant networks that maximize performance.
  arXiv  Detail & Related papers  (2021-04-10T19:37:25Z)
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution [57.635467829558664]
  We introduce a structural regularization across convolutional kernels in a CNN. We show that CNNs now maintain performance with dramatic reduction in parameters and computations.
  arXiv  Detail & Related papers  (2020-09-04T20:41:47Z)

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.