Geometric Autoencoders -- What You See is What You Decode

• URL: http://arxiv.org/abs/2306.17638v1
• Date: Fri, 30 Jun 2023 13:24:31 GMT
• Title: Geometric Autoencoders -- What You See is What You Decode
• Authors: Philipp Nazari, Sebastian Damrich, Fred A. Hamprecht
• Abstract summary: We propose a differential geometric perspective on the decoder, leading to insightful diagnostics for an embedding's distortion, and a new regularizer mitigating such distortion. Our Geometric Autoencoder'' avoids stretching the embedding spuriously, so that the visualization captures the data structure more faithfully.
• Score: 12.139222986297263
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visualization is a crucial step in exploratory data analysis. One possible approach is to train an autoencoder with low-dimensional latent space. Large network depth and width can help unfolding the data. However, such expressive networks can achieve low reconstruction error even when the latent representation is distorted. To avoid such misleading visualizations, we propose first a differential geometric perspective on the decoder, leading to insightful diagnostics for an embedding's distortion, and second a new regularizer mitigating such distortion. Our ``Geometric Autoencoder'' avoids stretching the embedding spuriously, so that the visualization captures the data structure more faithfully. It also flags areas where little distortion could not be achieved, thus guarding against misinterpretation.

Related papers

• $ε$-VAE: Denoising as Visual Decoding [61.29255979767292]
  In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. Current visual tokenization methods rely on a traditional autoencoder framework, where the encoder compresses data into latent representations, and the decoder reconstructs the original input. We propose denoising as decoding, shifting from single-step reconstruction to iterative refinement. Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image, guided by the latents provided by the encoder. We evaluate our approach by assessing both reconstruction (rFID) and generation quality (
  arXiv  Detail & Related papers  (2024-10-05T08:27:53Z)
• Decoder Decomposition for the Analysis of the Latent Space of Nonlinear Autoencoders With Wind-Tunnel Experimental Data [3.7960472831772765]
  The goal of this paper is to propose a method to aid the interpretability of autoencoders. We propose the decoder decomposition, which is a post-processing method to connect the latent variables to the coherent structures of flows. The ability to rank and select latent variables will help users design and interpret nonlinear autoencoders.
  arXiv  Detail & Related papers  (2024-04-25T10:09:37Z)
• Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth [83.15263499262824]
  We prove that gradient descent converges to a solution that completely disregards the sparse structure of the input. We show how to improve upon Gaussian performance for the compression of sparse data by adding a denoising function to a shallow architecture. We validate our findings on image datasets, such as CIFAR-10 and MNIST.
  arXiv  Detail & Related papers  (2024-02-07T16:32:29Z)
• AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation [51.143540967290114]
  We propose a method that unlocks a wide range of previously-infeasible geometric augmentations for unsupervised depth computation and estimation. This is achieved by reversing, or undo''-ing, geometric transformations to the coordinates of the output depth, warping the depth map back to the original reference frame.
  arXiv  Detail & Related papers  (2023-10-15T05:15:45Z)
• Adversarial robustness of VAEs through the lens of local geometry [1.2228014485474623]
  In an unsupervised attack on variational autoencoders (VAEs), an adversary finds a small perturbation in an input sample that significantly changes its latent space encoding. This paper demonstrates that an optimal way for an adversary to attack VAEs is to exploit a directional bias of a pullback metric tensor.
  arXiv  Detail & Related papers  (2022-08-08T05:53:57Z)
• Anomaly Detection with Adversarially Learned Perturbations of Latent Space [9.473040033926264]
  Anomaly detection is to identify samples that do not conform to the distribution of the normal data. In this work, we have designed an adversarial framework consisting of two competing components, an Adversarial Distorter, and an Autoencoder. The proposed method outperforms the existing state-of-the-art methods in anomaly detection on image and video datasets.
  arXiv  Detail & Related papers  (2022-07-03T19:32:00Z)
• Toward a Geometrical Understanding of Self-supervised Contrastive Learning [55.83778629498769]
  Self-supervised learning (SSL) is one of the premier techniques to create data representations that are actionable for transfer learning in the absence of human annotations. Mainstream SSL techniques rely on a specific deep neural network architecture with two cascaded neural networks: the encoder and the projector. In this paper, we investigate how the strength of the data augmentation policies affects the data embedding.
  arXiv  Detail & Related papers  (2022-05-13T23:24:48Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)
• A manifold learning perspective on representation learning: Learning decoder and representations without an encoder [0.0]
  Autoencoders are commonly used in representation learning. Inspired by manifold learning, we show that the decoder can be trained on its own by learning the representations of the training samples. Our approach of training the decoder alone facilitates representation learning even on small data sets.
  arXiv  Detail & Related papers  (2021-08-31T15:08:50Z)
• Modeling Lost Information in Lossy Image Compression [72.69327382643549]
  Lossy image compression is one of the most commonly used operators for digital images. We propose a novel invertible framework called Invertible Lossy Compression (ILC) to largely mitigate the information loss problem.
  arXiv  Detail & Related papers  (2020-06-22T04:04:56Z)
• Isometric Autoencoders [36.947436313489746]
  We advocate an isometry (i.e., local distance preserving) regularizer. Our regularizer encourages: (i.e., the decoder to be an isometry; and (ii) the encoder to be the decoder's pseudo-inverse, that is, the encoder extends the inverse of the decoder to the ambient space by projection.
  arXiv  Detail & Related papers  (2020-06-16T16:31:57Z)

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.