{"url":"/method/latent-optimisation","slug":"latent-optimisation","name":"Latent Optimisation","full_name":"Latent Optimisation","full_name_withheld":false,"description_markdown":"**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 $\\nabla\\_{z}f\\left(z\\right) = \\delta{f}\\left(z\\right)\\delta{z}$ points in the direction that better satisfies the discriminator $D$, which implies better samples. Therefore, instead of using the randomly sampled $z \\sim p\\left(z\\right)$, we uses the optimised latent:\r\n\r\n$$ \\Delta{z} = \\alpha\\frac{\\delta{f}\\left(z\\right)}{\\delta{z}} $$\r\n\r\n$$ z' = z + \\Delta{z} $$\r\n\r\nSource: [LOGAN](https://paperswithcode.com/method/logan)\r\n.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Deep Compressed Sensing","paper":"/paper/deep-compressed-sensing","first_author":"Yan Wu","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deep-compressed-sensing"},"source":{"url":"https://arxiv.org/abs/1905.06723v2","title":"Deep Compressed Sensing","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/deepmind/deepmind-research/blob/2160fc7f174a2d0ffe79aef5ca1b59419e4fafa1/cs_gan/utils.py#L89","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Latent Variable Sampling","url":"/methods/category/latent-variable-sampling","pwc_aliases":[]}],"n_papers_tagged":13,"archive_num_papers":13,"papers_newest_first":[{"paper":null,"title":"Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN","date":"2022-11-16","arxiv_id":"2211.08742","n_code_links":0,"syntology":null},{"paper":null,"title":"Edge-based fever screening system over private 5G","date":"2022-02-08","arxiv_id":"2202.03917","n_code_links":0,"syntology":null},{"paper":null,"title":"SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps","date":"2022-01-13","arxiv_id":"2201.05120","n_code_links":0,"syntology":null},{"paper":null,"title":"Sinogram Denoise Based on Generative Adversarial Networks","date":"2021-08-09","arxiv_id":"2108.03903","n_code_links":0,"syntology":null},{"paper":null,"title":"Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation","date":"2021-07-08","arxiv_id":"2107.03887","n_code_links":0,"syntology":null},{"paper":null,"title":"Direct Reconstruction of Linear Parametric Images from Dynamic PET Using Nonlocal Deep Image Prior","date":"2021-06-18","arxiv_id":"2106.10359","n_code_links":0,"syntology":null},{"paper":"/paper/mammoganesis-controlled-generation-of-high","title":"MammoGANesis: Controlled Generation of High-Resolution Mammograms for Radiology Education","date":"2020-10-11","arxiv_id":"2010.05177","n_code_links":1,"syntology":null},{"paper":"/paper/synthesising-clinically-realistic-chest-x","title":"Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs","date":"2020-10-07","arxiv_id":"2010.03975","n_code_links":1,"syntology":null},{"paper":"/paper/logan-local-group-bias-detection-by","title":"LOGAN: Local Group Bias Detection by Clustering","date":"2020-10-06","arxiv_id":"2010.02867","n_code_links":1,"syntology":null},{"paper":"/paper/deeplandscape-adversarial-modeling-of-1","title":"DeepLandscape: Adversarial Modeling of Landscape Videos","date":"2020-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Allpass Feedback Delay Networks","date":"2020-07-14","arxiv_id":"2007.07337","n_code_links":0,"syntology":null},{"paper":"/paper/logan-latent-optimisation-for-generative-1","title":"LOGAN: Latent Optimisation for Generative Adversarial Networks","date":"2019-12-02","arxiv_id":"1912.00953","n_code_links":1,"syntology":{"ran":2,"of":8,"unverified":6,"pointer_only":0}},{"paper":"/paper/deep-compressed-sensing","title":"Deep Compressed Sensing","date":"2019-05-16","arxiv_id":"1905.06723","n_code_links":1,"syntology":null}],"papers_shown":13,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":3},{"task":"/task/bias-detection","name":"Bias Detection","papers":2},{"task":"/task/clustering","name":"Clustering","papers":2},{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":2},{"task":null,"name":"Generative Adversarial Network","papers":2},{"task":"/task/medical-image-generation","name":"Medical Image Generation","papers":2},{"task":"/task/anatomy","name":"Anatomy","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/cardiac-segmentation","name":"Cardiac Segmentation","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/edge-computing","name":"Edge-computing","papers":1},{"task":"/task/ethics","name":"Ethics","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":"/task/meta-learning","name":"Meta-Learning","papers":1},{"task":"/task/radiologist-binary-classification","name":"Radiologist Binary Classification","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1}],"tasks_shown":20,"n_tasks":27,"usage_by_year":[{"year":"2019","papers":2},{"year":"2020","papers":5},{"year":"2021","papers":3},{"year":"2022","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/latent-optimisation"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}