Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization

• URL: http://arxiv.org/abs/2410.20573v1
• Date: Sun, 27 Oct 2024 19:56:02 GMT
• Title: Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization
• Authors: Mohammad Hassan Vali, Tom Bäckström,
• Abstract summary: Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Some earlier supervised methods aim to create an interpretable latent space or discover interpretable directions. We propose using a modification of vector quantization called space-filling vector quantization (SFVQ), which quantizes the data on a piece-wise linear curve.
• Score: 9.181917968017258
• License:
• Abstract: Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Such latent spaces are difficult to interpret. Some earlier supervised methods aim to create an interpretable latent space or discover interpretable directions that require exploiting data labels or annotated synthesized samples for training. However, we propose using a modification of vector quantization called space-filling vector quantization (SFVQ), which quantizes the data on a piece-wise linear curve. SFVQ can capture the underlying morphological structure of the latent space and thus make it interpretable. We apply this technique to model the latent space of pretrained StyleGAN2 and BigGAN networks on various datasets. Our experiments show that the SFVQ curve yields a general interpretable model of the latent space that determines which part of the latent space corresponds to what specific generative factors. Furthermore, we demonstrate that each line of SFVQ's curve can potentially refer to an interpretable direction for applying intelligible image transformations. We also showed that the points located on an SFVQ line can be used for controllable data augmentation.

Related papers

• Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts [68.48103545146127]
  This paper proposes a novel framework for unsupervised exploration of diffusion latent spaces. We directly leverage natural language prompts and image captions to map latent directions. Our method provides a more scalable and interpretable understanding of the semantic knowledge encoded within diffusion models.
  arXiv  Detail & Related papers  (2024-10-25T21:44:51Z)
• HoloNets: Spectral Convolutions do extend to Directed Graphs [59.851175771106625]
  Conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs. Here we show this traditional reliance on the graph Fourier transform to be superfluous. We provide a frequency-response interpretation of newly developed filters, investigate the influence of the basis used to express filters and discuss the interplay with characteristic operators on which networks are based.
  arXiv  Detail & Related papers  (2023-10-03T17:42:09Z)
• 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)
• Linear Variational State Space Filtering [3.1219977244201065]
  Variational State-Space Filters (VSSF) is a new method for unsupervised learning, identification, and filtering of latent Markov state space models from raw pixels. We present a theoretically sound framework for latent state space inference under heterogeneous sensor configurations. We experimentally demonstrate L-VSSF's ability to filter in latent space beyond the sequence length of the training dataset.
  arXiv  Detail & Related papers  (2022-01-04T21:28:32Z)
• Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs [7.443321740418409]
  We propose a method to find local-geometry-aware traversal directions on the intermediate latent space of Generative Adversarial Networks (GANs) Motivated by the intrinsic sparsity of the latent space, the basis is discovered by solving the low-rank approximation problem of the differential of the partial network.
  arXiv  Detail & Related papers  (2021-06-13T10:29:42Z)
• EXoN: EXplainable encoder Network [0.0]
  We propose a new semi-supervised learning method of Variational AutoEncoder (VAE) which yields explainable latent space by EXplainable encoder Network (EXoN) Negative cross-entropy and Kullback-Leibler divergence play a crucial role in constructing explainable latent space.
  arXiv  Detail & Related papers  (2021-05-23T07:04:30Z)
• EigenGAN: Layer-Wise Eigen-Learning for GANs [84.33920839885619]
  EigenGAN is able to unsupervisedly mine interpretable and controllable dimensions from different generator layers. By traversing the coefficient of a specific eigen-dimension, the generator can produce samples with continuous changes corresponding to a specific semantic attribute.
  arXiv  Detail & Related papers  (2021-04-26T11:14:37Z)
• Where and What? Examining Interpretable Disentangled Representations [96.32813624341833]
  Capturing interpretable variations has long been one of the goals in disentanglement learning. Unlike the independence assumption, interpretability has rarely been exploited to encourage disentanglement in the unsupervised setting. In this paper, we examine the interpretability of disentangled representations by investigating two questions: where to be interpreted and what to be interpreted.
  arXiv  Detail & Related papers  (2021-04-07T11:22:02Z)
• The Geometry of Deep Generative Image Models and its Applications [0.0]
  Generative adversarial networks (GANs) have emerged as a powerful unsupervised method to model the statistical patterns of real-world data sets. These networks are trained to map random inputs in their latent space to new samples representative of the learned data. The structure of the latent space is hard to intuit due to its high dimensionality and the non-linearity of the generator.
  arXiv  Detail & Related papers  (2021-01-15T07:57:33Z)
• IntroVAC: Introspective Variational Classifiers for Learning Interpretable Latent Subspaces [6.574517227976925]
  IntroVAC learns interpretable latent subspaces by exploiting information from an additional label. We show that IntroVAC is able to learn meaningful directions in the latent space enabling fine manipulation of image attributes.
  arXiv  Detail & Related papers  (2020-08-03T10:21:41Z)
• Semi-Supervised Learning with Normalizing Flows [54.376602201489995]
  FlowGMM is an end-to-end approach to generative semi supervised learning with normalizing flows. We show promising results on a wide range of applications, including AG-News and Yahoo Answers text data.
  arXiv  Detail & Related papers  (2019-12-30T17:36:33Z)

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.