mlsanityData to 7 Oct 2026

LCIP: Loss-Controlled Inverse Projection of High-Dimensional Image Data

arXiv 2602.11141 ↗First posted 11 Feb 2026cs.HC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Projections (or dimensionality reduction) methods P aim to map high-dimensional data to typically 2D scatterplots for visual exploration. Inverse projection methods P-1 aim to map this 2D space to the data space to support tasks such as data augmentation, classifier analysis, and data imputation. Current P-1 methods suffer from a fundamental limitation -- they can only generate a fixed surface-like structure in data space, which poorly covers the richness of this space. We address this by a new method that can `sweep' the data space under user control. Our method works generically for any P technique and dataset, is controlled by two intuitive user-set parameters, and is simple to implement. We demonstrate it by an extensive application involving image manipulation for style transfer.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 53 references that are in the map. First posted on arXiv 11 Feb 2026.

Builds on

22 of 53 references.

References · 22

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  7. 2019Intrinsic dimension of data representations in deep neural networkscited by 276
  8. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  9. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  10. 2018Invariant Representations without Adversarial Trainingcited by 111
  11. 2016Disentangling factors of variation in deep representations using adversarial trainingcited by 87
  12. 2014A survey of dimensionality reduction techniquescited by 50
10 more
  1. 2020t-viSNE: Interactive Assessment and Interpretation of t-SNE Projectionscited by 43
  2. 2018Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensionscited by 19
  3. 2018Unsupervised Adversarial Invariancecited by 14
  4. 2019Deep Learning Multidimensional Projectionscited by 14
  5. 2017A Two-Step Disentanglement Methodcited by 13
  6. 2021UnProjection: Leveraging Inverse-Projections for Visual Analytics of High-Dimensional Datacited by 8
  7. 2020Effect of Input Noise Dimension in GANscited by 6
  8. 2019Unified Adversarial Invariancecited by 4
  9. 2025Evaluating Autoencoders for Parametric and Invertible Multidimensional Projectionscited by 4
  10. 2023Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representationscited by 1

Built on by

Not cited yet.