Scale generalisation properties of extended scale-covariant and scale-invariant Gaussian derivative networks on image datasets with spatial scaling variations

• URL: http://arxiv.org/abs/2409.11140v2
• Date: Tue, 25 Mar 2025 10:38:59 GMT
• Title: Scale generalisation properties of extended scale-covariant and scale-invariant Gaussian derivative networks on image datasets with spatial scaling variations
• Authors: Andrzej Perzanowski, Tony Lindeberg,
• Abstract summary: GaussDerNets are evaluated on new rescaled versions of the Fashion-MNIST and the CIFAR-10 datasets.<n>We first experimentally demonstrate that the GaussDerNets have quite good scale generalisation properties on the new datasets.<n>We also show that regularisation during training, by applying dropout across the scale channels, improves both the performance and the scale generalisation.
• Score: 0.46040036610482665
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents an in-depth analysis of the scale generalisation properties of the scale-covariant and scale-invariant Gaussian derivative networks, complemented with both conceptual and algorithmic extensions. For this purpose, Gaussian derivative networks (GaussDerNets) are evaluated on new rescaled versions of the Fashion-MNIST and the CIFAR-10 datasets, with spatial scaling variations over a factor of 4 in the testing data, that are not present in the training data. Additionally, evaluations on the previously existing STIR datasets show that the GaussDerNets achieve better scale generalisation than previously reported for these datasets for other types of deep networks. We first experimentally demonstrate that the GaussDerNets have quite good scale generalisation properties on the new datasets, and that average pooling of feature responses over scales may sometimes also lead to better results than the previously used approach of max pooling over scales. Then, we demonstrate that using a spatial max pooling mechanism after the final layer enables localisation of non-centred objects in image domain, with maintained scale generalisation properties. We also show that regularisation during training, by applying dropout across the scale channels, referred to as scale-channel dropout, improves both the performance and the scale generalisation. In additional ablation studies, we demonstrate that discretisations of GaussDerNets, based on the discrete analogue of the Gaussian kernel in combination with central difference operators, perform best or among the best, compared to a set of other discrete approximations of the Gaussian derivative kernels. Finally, by visualising the activation maps and the learned receptive fields, we demonstrate that the GaussDerNets have very good explainability properties.

Related papers

• Scale-invariant Gaussian derivative residual networks [4.554894288663752]
  Generalisation across image scales remains a fundamental challenge for deep networks.<n>We present provably scale-invariant Gaussian derivative residual networks (GaussDerResNets)<n>We show that GaussDerResNets have strong scale generalisation and scale selection properties on rescaled datasets.
  arXiv  Detail & Related papers  (2026-03-03T10:39:41Z)
• Investigating generalization capabilities of neural networks by means of loss landscapes and Hessian analysis [0.0]
  This paper studies generalization capabilities of neural networks (NNs) using new and improved PyTorch library Loss Landscape Analysis (LLA) LLA facilitates visualization and analysis of loss landscapes along with the properties of NN Hessian.
  arXiv  Detail & Related papers  (2024-12-13T14:02:41Z)
• Nonuniform random feature models using derivative information [10.239175197655266]
  We propose nonuniform data-driven parameter distributions for neural network initialization based on derivative data of the function to be approximated. We address the cases of Heaviside and ReLU activation functions, and their smooth approximations (sigmoid and softplus) We suggest simplifications of these exact densities based on approximate derivative data in the input points that allow for very efficient sampling and lead to performance of random feature models close to optimal networks in several scenarios.
  arXiv  Detail & Related papers  (2024-10-03T01:30:13Z)
• Generalization of Geometric Graph Neural Networks [84.01980526069075]
  We study the generalization capabilities of geometric graph neural networks (GNNs) We prove a generalization gap between the optimal empirical risk and the optimal statistical risk of this GNN. The most important observation is that the generalization capability can be realized with one large graph instead of being limited to the size of the graph as in previous results.
  arXiv  Detail & Related papers  (2024-09-08T18:55:57Z)
• ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining [104.34751911174196]
  We build a large-scale dataset of 3DGS using ShapeNet and ModelNet datasets. Our dataset ShapeSplat consists of 65K objects from 87 unique categories. We introduce textbftextitGaussian-MAE, which highlights the unique benefits of representation learning from Gaussian parameters.
  arXiv  Detail & Related papers  (2024-08-20T14:49:14Z)
• Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets [1.8434042562191815]
  We derive expressions for the Bayes optimal decision boundaries in binary classification of high dimensional overlapping Gaussian mixture model (GMM) data. We empirically demonstrate, through experiments on synthetic GMMs inspired by real-world data, that deep neural networks trained for classification, learn predictors which approximate the derived optimal classifiers.
  arXiv  Detail & Related papers  (2024-05-28T17:59:31Z)
• RGM: A Robust Generalizable Matching Model [49.60975442871967]
  We propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching) To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth. We are able to mix up various dense and sparse matching datasets, significantly improving the training diversity.
  arXiv  Detail & Related papers  (2023-10-18T07:30:08Z)
• Neural Tangent Kernels Motivate Graph Neural Networks with Cross-Covariance Graphs [94.44374472696272]
  We investigate NTKs and alignment in the context of graph neural networks (GNNs) Our results establish the theoretical guarantees on the optimality of the alignment for a two-layer GNN. These guarantees are characterized by the graph shift operator being a function of the cross-covariance between the input and the output data.
  arXiv  Detail & Related papers  (2023-10-16T19:54:21Z)
• VTAE: Variational Transformer Autoencoder with Manifolds Learning [144.0546653941249]
  Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables. The nonlinearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. We show that geodesics and accurate computation can substantially improve the performance of deep generative models.
  arXiv  Detail & Related papers  (2023-04-03T13:13:19Z)
• Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning [4.644263115284322]
  Graph neural networks (GNNs) emerged recently as a promising class of models for graph-structured data in semi-supervised learning. We introduce this inductive bias into GPs to improve their predictive performance for graph-structured data. We show that these graph-based kernels lead to competitive classification and regression performance, as well as advantages in time, compared with the respective GNNs.
  arXiv  Detail & Related papers  (2023-02-12T01:07:56Z)
• Bayesian Interpolation with Deep Linear Networks [92.1721532941863]
  Characterizing how neural network depth, width, and dataset size jointly impact model quality is a central problem in deep learning theory. We show that linear networks make provably optimal predictions at infinite depth. We also show that with data-agnostic priors, Bayesian model evidence in wide linear networks is maximized at infinite depth.
  arXiv  Detail & Related papers  (2022-12-29T20:57:46Z)
• Beyond permutation equivariance in graph networks [1.713291434132985]
  We introduce a novel architecture for graph networks which is equivariant to the Euclidean group in $n$-dimensions. Our model is designed to work with graph networks in their most general form, thus including particular variants as special cases.
  arXiv  Detail & Related papers  (2021-03-25T18:36:09Z)
• Scale-covariant and scale-invariant Gaussian derivative networks [0.0]
  This paper presents a hybrid approach between scale-space theory and deep learning, where a deep learning architecture is constructed by coupling parameterized scale-space operations in cascade. It is demonstrated that the resulting approach allows for scale generalization, enabling good performance for classifying patterns at scales not present in the training data.
  arXiv  Detail & Related papers  (2020-11-30T13:15:10Z)
• Improving predictions of Bayesian neural nets via local linearization [79.21517734364093]
  We argue that the Gauss-Newton approximation should be understood as a local linearization of the underlying Bayesian neural network (BNN) Because we use this linearized model for posterior inference, we should also predict using this modified model instead of the original one. We refer to this modified predictive as "GLM predictive" and show that it effectively resolves common underfitting problems of the Laplace approximation.
  arXiv  Detail & Related papers  (2020-08-19T12:35:55Z)
• Towards GANs' Approximation Ability [8.471366736328811]
  This paper will first theoretically analyze GANs' approximation property. We prove that the generator with the input latent variable in GANs can universally approximate the potential data distribution. In the practical dataset, four GANs using SDG can also outperform the corresponding traditional GANs when the model architectures are smaller.
  arXiv  Detail & Related papers  (2020-04-10T02:40:16Z)
• Infinitely Wide Graph Convolutional Networks: Semi-supervised Learning via Gaussian Processes [144.6048446370369]
  Graph convolutional neural networks(GCNs) have recently demonstrated promising results on graph-based semi-supervised classification. We propose a GP regression model via GCNs(GPGC) for graph-based semi-supervised learning. We conduct extensive experiments to evaluate GPGC and demonstrate that it outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-02-26T10:02:32Z)
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization [56.69671152009899]
  We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization. We also propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction.
  arXiv  Detail & Related papers  (2020-02-20T15:13:27Z)

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.