How deep convolutional neural networks lose spatial information with training

• URL: http://arxiv.org/abs/2210.01506v1
• Date: Tue, 4 Oct 2022 10:21:03 GMT
• Title: How deep convolutional neural networks lose spatial information with training
• Authors: Umberto M. Tomasini, Leonardo Petrini, Francesco Cagnetta, Matthieu Wyart
• Abstract summary: We show how stability to image diffeomorphisms is achieved by spatial pooling in the first half of the net, and by channel pooling in the second half. We find that the increased sensitivity to noise is due to the perturbing noise piling up during pooling, after being rectified by ReLU units.
• Score: 0.7328100870402177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A central question of machine learning is how deep nets manage to learn tasks in high dimensions. An appealing hypothesis is that they achieve this feat by building a representation of the data where information irrelevant to the task is lost. For image datasets, this view is supported by the observation that after (and not before) training, the neural representation becomes less and less sensitive to diffeomorphisms acting on images as the signal propagates through the net. This loss of sensitivity correlates with performance, and surprisingly correlates with a gain of sensitivity to white noise acquired during training. These facts are unexplained, and as we demonstrate still hold when white noise is added to the images of the training set. Here, we (i) show empirically for various architectures that stability to image diffeomorphisms is achieved by spatial pooling in the first half of the net, and by channel pooling in the second half, (ii) introduce a scale-detection task for a simple model of data where pooling is learned during training, which captures all empirical observations above and (iii) compute in this model how stability to diffeomorphisms and noise scale with depth. The scalings are found to depend on the presence of strides in the net architecture. We find that the increased sensitivity to noise is due to the perturbing noise piling up during pooling, after being rectified by ReLU units.

Related papers

• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture. We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy [55.014926694758195]
  Entropy and mutual information in neural networks provide rich information on the learning process. We leverage data geometry to access the underlying manifold and reliably compute these information-theoretic measures. We show that they form noise-resistant measures of intrinsic dimensionality and relationship strength in high-dimensional simulated data.
  arXiv  Detail & Related papers  (2023-12-04T01:32:42Z)
• Generalization in diffusion models arises from geometry-adaptive harmonic representations [21.384922363202335]
  Deep neural networks (DNNs) trained for image denoising are able to generate high-quality samples with score-based reverse diffusion algorithms. Recent reports of memorization of the training set raise the question of whether these networks are learning the "true" continuous density of the data. We show that two DNNs trained on non-overlapping subsets of a dataset learn nearly the same score function, and thus the same density, when the number of training images is large enough.
  arXiv  Detail & Related papers  (2023-10-04T03:30:32Z)
• Ambiguity in solving imaging inverse problems with deep learning based operators [0.0]
  Large convolutional neural networks have been widely used as tools for image deblurring. Image deblurring is mathematically modeled as an ill-posed inverse problem and its solution is difficult to approximate when noise affects the data. In this paper, we propose some strategies to improve stability without losing to much accuracy to deblur images with deep-learning based methods.
  arXiv  Detail & Related papers  (2023-05-31T12:07:08Z)
• Deep Semantic Statistics Matching (D2SM) Denoising Network [70.01091467628068]
  We introduce the Deep Semantic Statistics Matching (D2SM) Denoising Network. It exploits semantic features of pretrained classification networks, then it implicitly matches the probabilistic distribution of clear images at the semantic feature space. By learning to preserve the semantic distribution of denoised images, we empirically find our method significantly improves the denoising capabilities of networks.
  arXiv  Detail & Related papers  (2022-07-19T14:35:42Z)
• Learning sparse features can lead to overfitting in neural networks [9.2104922520782]
  We show that feature learning can perform worse than lazy training. Although sparsity is known to be essential for learning anisotropic data, it is detrimental when the target function is constant or smooth.
  arXiv  Detail & Related papers  (2022-06-24T14:26:33Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations [71.00754846434744]
  We show that imperceptible additive perturbations can significantly alter the disparity map. We show that, when used for adversarial data augmentation, our perturbations result in trained models that are more robust.
  arXiv  Detail & Related papers  (2020-09-21T19:20:09Z)
• Identity Enhanced Residual Image Denoising [61.75610647978973]
  We learn a fully-convolutional network model that consists of a Chain of Identity Mapping Modules and residual on the residual architecture for image denoising. The proposed network produces remarkably higher numerical accuracy and better visual image quality than the classical state-of-the-art and CNN algorithms.
  arXiv  Detail & Related papers  (2020-04-26T04:52:22Z)
• Extracting dispersion curves from ambient noise correlations using deep learning [1.0237120900821557]
  We present a machine-learning approach to classifying the phases of surface wave dispersion curves. Standard FTAN analysis of surfaces observed on an array of receivers is converted to an image. We use a convolutional neural network (U-net) architecture with a supervised learning objective and incorporate transfer learning.
  arXiv  Detail & Related papers  (2020-02-05T23:41:12Z)

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.