Methods › General › Latent Variable Sampling › Latent Optimisation
Latent Optimisation
Introduced by Yan Wu et al. in Deep Compressed Sensing
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Latent Optimisation is a technique used for generative adversarial networks to refine the sample quality of z. Specifically, it exploits knowledge from the discriminator D to refine the latent source z. Intuitively, the gradient ∇_zf(z) = δf(z)δz points in the direction that better satisfies the discriminator D, which implies better samples. Therefore, instead of using the randomly sampled z ∼p(z), we uses the optimised latent:
Δz = α(δf(z))/δz
z′ = z + Δz
Source: LOGAN .
Papers archive 2025-07-28
13 shown of 13, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN 16 Nov 2022 · 0 repositories · arXiv:2211.08742
-
Edge-based fever screening system over private 5G 8 Feb 2022 · 0 repositories · arXiv:2202.03917
-
SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps 13 Jan 2022 · 0 repositories · arXiv:2201.05120
-
Sinogram Denoise Based on Generative Adversarial Networks 9 Aug 2021 · 0 repositories · arXiv:2108.03903
-
Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation 8 Jul 2021 · 0 repositories · arXiv:2107.03887
-
Direct Reconstruction of Linear Parametric Images from Dynamic PET Using Nonlocal Deep Image Prior 18 Jun 2021 · 0 repositories · arXiv:2106.10359
-
MammoGANesis: Controlled Generation of High-Resolution Mammograms for Radiology Education 11 Oct 2020 · 1 repository · arXiv:2010.05177
-
Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs 7 Oct 2020 · 1 repository · arXiv:2010.03975
-
LOGAN: Local Group Bias Detection by Clustering 6 Oct 2020 · 1 repository · arXiv:2010.02867
-
DeepLandscape: Adversarial Modeling of Landscape Videos 1 Aug 2020 · 1 repository
-
Allpass Feedback Delay Networks 14 Jul 2020 · 0 repositories · arXiv:2007.07337
-
LOGAN: Latent Optimisation for Generative Adversarial Networks 2 Dec 2019 · 1 repository · arXiv:1912.00953Syntology ran 2 of 8 samples · 6 unverified
-
Deep Compressed Sensing 16 May 2019 · 1 repository · arXiv:1905.06723
Tasks archive 2025-07-28
20 shown of 27 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Image Generation | 3 |
| Bias Detection | 2 |
| Clustering | 2 |
| Conditional Image Generation | 2 |
| Generative Adversarial Network | 2 |
| Medical Image Generation | 2 |
| Anatomy | 1 |
| Attribute | 1 |
| BIG-bench Machine Learning | 1 |
| Cardiac Segmentation | 1 |
| Computational Efficiency | 1 |
| Data Augmentation | 1 |
| Denoising | 1 |
| Diagnostic | 1 |
| Edge-computing | 1 |
| Ethics | 1 |
| Fairness | 1 |
| Meta-Learning | 1 |
| Radiologist Binary Classification | 1 |
| Segmentation | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections