Methods › Computer Vision › Generative Models › SIG
Sliced Iterative Generator
SIG
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The Sliced Iterative Generator (SIG) is an iterative generative model that is a Normalizing Flow (NF), but shares the advantages of Generative Adversarial Networks (GANs). The model is based on iterative Optimal Transport of a series of 1D slices through the data space, matching on each slice the probability distribution function (PDF) of the samples to the data. To improve the efficiency, the directions of the orthogonal slices are chosen to maximize the PDF difference between the generated samples and the data using Wasserstein distance at each iteration. A patch based approach is adopted to model the images in a hierarchical way, enabling the model to scale well to high dimensions.
Unlike GANs, SIG has a NF structure and allows efficient likelihood evaluations that can be used in downstream tasks. While SIG has a deep neural network architecture, the approach deviates significantly from the current deep learning paradigm, as it does not use concepts such as mini-batching, stochastic gradient descent, gradient back-propagation through deep layers, or non-convex loss function optimization. SIG is very insensitive to hyper-parameter tuning, making it a useful generator tool for ML experts and non-experts alike.
Papers archive 2025-07-28
17 shown of 17, 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.
-
Quality Assessment of Noisy and Enhanced Speech with Limited Data: UWB-NTIS System for VoiceMOS 2024 and Beyond 31 May 2025 · 0 repositories · arXiv:2506.00506
-
Keras Sig: Efficient Path Signature Computation on GPU in Keras 3 14 Jan 2025 · 0 repositories · arXiv:2501.08455
-
SIG: A Synthetic Identity Generation Pipeline for Generating Evaluation Datasets for Face Recognition 12 Sep 2024 · 0 repositories · arXiv:2409.08345
-
Enhancing Safety for Autonomous Agents in Partly Concealed Urban Traffic Environments Through Representation-Based Shielding 5 Jul 2024 · 1 repository · arXiv:2407.04343
-
Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework 10 Feb 2024 · 0 repositories · arXiv:2402.06875
-
SIG: Speaker Identification in Literature via Prompt-Based Generation 22 Dec 2023 · 1 repository · arXiv:2312.14590
-
A New Baseline Assumption of Integated Gradients Based on Shaply value 7 Oct 2023 · 0 repositories · arXiv:2310.04821
-
Subspace Identification for Multi-Source Domain Adaptation 7 Oct 2023 · 1 repository · arXiv:2310.04723Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
-
Position and Orientation-Aware One-Shot Learning for Medical Action Recognition from Signal Data 27 Sep 2023 · 0 repositories · arXiv:2309.15635
-
Sequential Integrated Gradients: a simple but effective method for explaining language models 25 May 2023 · 1 repository · arXiv:2305.15853
-
ICASSP 2023 Speech Signal Improvement Challenge 12 Mar 2023 · 0 repositories · arXiv:2303.06566
-
CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis 28 Feb 2023 · 0 repositories · arXiv:2302.14370
-
PetsGAN: Rethinking Priors for Single Image Generation 3 Mar 2022 · 2 repositories · arXiv:2203.01488
-
ICASSP 2022 Deep Noise Suppression Challenge 27 Feb 2022 · 1 repository · arXiv:2202.13288Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
-
Aura: Privacy-preserving Augmentation to Improve Test Set Diversity in Speech Enhancement 8 Oct 2021 · 1 repository · arXiv:2110.04391
-
DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors 5 Oct 2021 · 1 repository · arXiv:2110.01763
-
Sliced Iterative Normalizing Flows 1 Jul 2020 · 2 repositories · arXiv:2007.00674Syntology ran 1 of 4 samples · 3 unverified · 4 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 32 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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