Methods › General › Normalization › Weight Demodulation
Weight Demodulation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Weight Modulation is an alternative to adaptive instance normalization for use in generative adversarial networks, specifically it is introduced in StyleGAN2. The purpose of instance normalization is to remove the effect of s - the scales of the features maps - from the statistics of the convolution’s output feature maps. Weight modulation tries to achieve this goal more directly. Assuming that input activations are i.i.d. random variables with unit standard deviation. After modulation and convolution, the output activations have standard deviation of:
σⱼ = √(∑_(i,k)wᵢⱼₖ′²)
i.e., the outputs are scaled by the L₂ norm of the corresponding weights. The subsequent normalization aims to restore the outputs back to unit standard deviation. This can be achieved if we scale (“demodulate”) each output feature map j by 1/σⱼ . Alternatively, we can again bake this into the convolution weights:
w″ᵢⱼₖ = w′ᵢⱼₖ / √(∑_(i, k)w′ᵢⱼₖ² + ϵ)
where ϵ is a small constant to avoid numerical issues.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: Weight Mixup; weight scaling; Weight Weaving; Weight Balancing; weight operators; Weight Recycling; Filter-then-Weight; Optimal Weight (OW).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 182 · with a code link: 108 · where Syntology ran a sample: 34 (28 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (34 of 182 tagged: 28 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 182, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Pose and Facial Expression Transfer by using StyleGAN 17 Apr 2025 · 0 repositories · arXiv:2504.13021
-
The GAN is dead; long live the GAN! A Modern GAN Baseline 9 Jan 2025 · 1 repository · arXiv:2501.05441Syntology official (archive's flag): 9 ran · 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples) · 11 pointer-only (licence)
-
Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement 23 Dec 2024 · 1 repository · arXiv:2412.17387
-
MyTimeMachine: Personalized Facial Age Transformation 21 Nov 2024 · 0 repositories · arXiv:2411.14521
-
Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization 27 Oct 2024 · 1 repository · arXiv:2410.20573
-
Stool Recognition for Colorectal Cancer Detection through Deep Learning 19 Oct 2024 · 0 repositories · arXiv:2410.17288
-
MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance 17 Sep 2024 · 1 repository · arXiv:2409.11010
-
Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture 28 Jul 2024 · 0 repositories · arXiv:2407.19593
-
Face Reconstruction Transfer Attack as Out-of-Distribution Generalization 2 Jul 2024 · 1 repository · arXiv:2407.02403
-
Controlling Face's Frame generation in StyleGAN's latent space operations: Modifying faces to deceive our memory 30 Jun 2024 · 0 repositories · arXiv:2407.00803
-
Analyzing the Feature Extractor Networks for Face Image Synthesis 4 Jun 2024 · 1 repository · arXiv:2406.02153
-
Nickel and Diming Your GAN: A Dual-Method Approach to Enhancing GAN Efficiency via Knowledge Distillation 19 May 2024 · 0 repositories · arXiv:2405.11614
-
Sampling Strategies for Mitigating Bias in Face Synthesis Methods 18 May 2024 · 0 repositories · arXiv:2405.11320
-
The Impact of Print-Scanning in Heterogeneous Morph Evaluation Scenarios 9 Apr 2024 · 0 repositories · arXiv:2404.06559
-
LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping 28 Feb 2024 · 1 repository · arXiv:2402.18351
-
Geometry aware 3D generation from in-the-wild images in ImageNet 31 Jan 2024 · 0 repositories · arXiv:2402.00225
-
UniHDA: A Unified and Versatile Framework for Multi-Modal Hybrid Domain Adaptation 23 Jan 2024 · 0 repositories · arXiv:2401.12596
-
HuRef: HUman-REadable Fingerprint for Large Language Models 8 Dec 2023 · 1 repository · arXiv:2312.04828Syntology official (archive's flag): 3 ran · 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Synthetic Speaking Children -- Why We Need Them and How to Make Them 8 Nov 2023 · 0 repositories · arXiv:2311.06307
-
On Measuring Fairness in Generative Models 30 Oct 2023 · 0 repositories · arXiv:2310.19297
-
Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning 6 Oct 2023 · 0 repositories · arXiv:2310.04194
-
FG-Net: Facial Action Unit Detection with Generalizable Pyramidal Features 23 Aug 2023 · 1 repository · arXiv:2308.12380
-
Fair GANs through model rebalancing for extremely imbalanced class distributions 16 Aug 2023 · 0 repositories · arXiv:2308.08638
-
ChildGAN: Large Scale Synthetic Child Facial Data Using Domain Adaptation in StyleGAN 25 Jul 2023 · 0 repositories · arXiv:2307.13746
-
HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces 20 Jul 2023 · 1 repository · arXiv:2307.10797Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
StyleGAN3: Generative Networks for Improving the Equivariance of Translation and Rotation 8 Jul 2023 · 0 repositories · arXiv:2307.03898
-
Seeing is not Believing: An Identity Hider for Human Vision Privacy Protection 2 Jul 2023 · 1 repository · arXiv:2307.00481
-
Deep Learning for Cancer Prognosis Prediction Using Portrait Photos by StyleGAN Embedding 26 Jun 2023 · 0 repositories · arXiv:2306.14596
-
F?D: On understanding the role of deep feature spaces on face generation evaluation 31 May 2023 · 0 repositories · arXiv:2305.20048
-
BRICS: Bi-level feature Representation of Image CollectionS 29 May 2023 · 0 repositories · arXiv:2305.18601
-
Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training 12 May 2023 · 2 repositories · arXiv:2305.07613Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Zero-shot racially balanced dataset generation using an existing biased StyleGAN2 12 May 2023 · 1 repository · arXiv:2305.07710
-
Improving Synthetically Generated Image Detection in Cross-Concept Settings 24 Apr 2023 · 1 repository · arXiv:2304.12053
-
PG-VTON: A Novel Image-Based Virtual Try-On Method via Progressive Inference Paradigm 18 Apr 2023 · 1 repository · arXiv:2304.08956
-
Attributing Image Generative Models using Latent Fingerprints 17 Apr 2023 · 1 repository · arXiv:2304.09752
-
ID2image: Leakage of non-ID information into face descriptors and inversion from descriptors to images 15 Apr 2023 · 0 repositories · arXiv:2304.07522
-
PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face Inpainting 12 Apr 2023 · 2 repositories · arXiv:2304.06107
-
Deepfake Detection of Occluded Images Using a Patch-based Approach 10 Apr 2023 · 0 repositories · arXiv:2304.04537
-
PrefGen: Preference Guided Image Generation with Relative Attributes 1 Apr 2023 · 1 repository · arXiv:2304.00185
-
Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instances 27 Mar 2023 · 0 repositories · arXiv:2303.15533
-
Spatial Latent Representations in Generative Adversarial Networks for Image Generation 25 Mar 2023 · 0 repositories · arXiv:2303.14552
-
Wasserstein Loss for Semantic Editing in the Latent Space of GANs 22 Mar 2023 · 0 repositories · arXiv:2304.10508
-
CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing 9 Mar 2023 · 0 repositories · arXiv:2303.05031
-
RiDDLE: Reversible and Diversified De-identification with Latent Encryptor 9 Mar 2023 · 1 repository · arXiv:2303.05171
-
End-to-end Face-swapping via Adaptive Latent Representation Learning 7 Mar 2023 · 0 repositories · arXiv:2303.04186
-
Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation 4 Mar 2023 · 1 repository · arXiv:2303.02389
-
Gradient Adjusting Networks for Domain Inversion 22 Feb 2023 · 1 repository · arXiv:2302.11413
-
One-Shot Face Video Re-enactment using Hybrid Latent Spaces of StyleGAN2 15 Feb 2023 · 0 repositories · arXiv:2302.07848
-
Conceptual and Hierarchical Latent Space Decomposition for Face Editing 1 Jan 2023 · 0 repositories
-
Robust One-Shot Face Video Re-enactment using Hybrid Latent Spaces of StyleGAN2 1 Jan 2023 · 0 repositories
-
StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis 1 Jan 2023 · 1 repository
-
Album cover art image generation with Generative Adversarial Networks 9 Dec 2022 · 0 repositories · arXiv:2212.04844
-
GLeaD: Improving GANs with A Generator-Leading Task 7 Dec 2022 · 1 repository · arXiv:2212.03752Syntology official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Brain Tumor Synthetic Data Generation with Adaptive StyleGANs 4 Dec 2022 · 1 repository · arXiv:2212.01772
-
Dense Interspecies Face Embedding 28 Nov 2022 · 1 repository
-
Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution 25 Nov 2022 · 0 repositories · arXiv:2211.13964
-
ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation 25 Nov 2022 · 1 repository · arXiv:2211.13974
-
Unsupervised Anomaly Appraisal of Cleft Faces Using a StyleGAN2-based Model Adaptation Technique 12 Nov 2022 · 0 repositories · arXiv:2211.06659
-
An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design 27 Oct 2022 · 0 repositories · arXiv:2210.15765
-
Atlas flow : compatible local structures on the manifold 24 Oct 2022 · 0 repositories · arXiv:2210.14149
-
Improving GANs with a Feature Cycling Generator 18 Oct 2022 · 0 repositories · arXiv:2210.09638
-
Intra-Source Style Augmentation for Improved Domain Generalization 18 Oct 2022 · 1 repository · arXiv:2210.10175
-
Landmark Enforcement and Style Manipulation for Generative Morphing 18 Oct 2022 · 0 repositories · arXiv:2210.10182
-
HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks 17 Oct 2022 · 1 repository · arXiv:2210.08884Syntology official (archive's flag): 8 ran · 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified (of 16 harvested samples)
-
MultiStyleGAN: Multiple One-shot Image Stylizations using a Single GAN 8 Oct 2022 · 0 repositories · arXiv:2210.04120
-
StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment 27 Sep 2022 · 1 repository · arXiv:2209.13375
-
StyleSwap: Style-Based Generator Empowers Robust Face Swapping 27 Sep 2022 · 0 repositories · arXiv:2209.13514
-
Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models 14 Sep 2022 · 1 repository · arXiv:2209.06970
-
Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models 30 Aug 2022 · 1 repository · arXiv:2208.14133
-
Mind the Gap in Distilling StyleGANs 18 Aug 2022 · 1 repository · arXiv:2208.08840
-
Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment 16 Aug 2022 · 1 repository · arXiv:2208.07765
-
HyperNST: Hyper-Networks for Neural Style Transfer 9 Aug 2022 · 0 repositories · arXiv:2208.04807
-
Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels 31 Jul 2022 · 1 repository · arXiv:2208.00439
-
Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval 29 Jul 2022 · 0 repositories · arXiv:2207.14428
-
Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms 25 Jun 2022 · 1 repository · arXiv:2206.12563
-
SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation 24 Jun 2022 · 1 repository · arXiv:2206.12055Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)
-
StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis 19 Jun 2022 · 2 repositories · arXiv:2206.09479Syntology official (archive's flag): 1 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples) · 2 pointer-only (licence)
-
Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing 16 Jun 2022 · 1 repository · arXiv:2206.08357Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior 28 May 2022 · 0 repositories · arXiv:2205.14377
-
Looks Like Magic: Transfer Learning in GANs to Generate New Card Illustrations 28 May 2022 · 0 repositories · arXiv:2205.14442
-
Text-to-Face Generation with StyleGAN2 25 May 2022 · 0 repositories · arXiv:2205.12512
-
Are GAN-based Morphs Threatening Face Recognition? 5 May 2022 · 1 repository · arXiv:2205.02496
-
BlobGAN: Spatially Disentangled Scene Representations 5 May 2022 · 0 repositories · arXiv:2205.02837
-
Generative Adversarial Network Based Synthetic Learning and a Novel Domain Relevant Loss Term for Spine Radiographs 5 May 2022 · 0 repositories · arXiv:2205.02843
-
BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images 3 May 2022 · 1 repository · arXiv:2205.01536
-
Evolutionary latent space search for driving human portrait generation 25 Apr 2022 · 0 repositories · arXiv:2204.11887
-
StyleT2F: Generating Human Faces from Textual Description Using StyleGAN2 17 Apr 2022 · 1 repository · arXiv:2204.07924
-
PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets 7 Apr 2022 · 0 repositories · arXiv:2204.05114
-
Thermal to Visible Image Synthesis under Atmospheric Turbulence 6 Apr 2022 · 0 repositories · arXiv:2204.03057
-
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation 2 Apr 2022 · 1 repository · arXiv:2204.00833
-
Expressive Talking Head Video Encoding in StyleGAN2 Latent-Space 28 Mar 2022 · 2 repositories · arXiv:2203.14512
-
Robust deep learning for eye fundus images: Bridging real and synthetic data for enhancing generalization 25 Mar 2022 · 2 repositories · arXiv:2203.13856
-
A naive method to discover directions in the StyleGAN2 latent space 19 Mar 2022 · 1 repository · arXiv:2203.10373
-
Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs 16 Mar 2022 · 0 repositories · arXiv:2203.08516
-
The Role of ImageNet Classes in Fréchet Inception Distance 11 Mar 2022 · 2 repositories · arXiv:2203.06026
-
Region-Aware Face Swapping 9 Mar 2022 · 0 repositories · arXiv:2203.04564
-
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values 3 Mar 2022 · 1 repository · arXiv:2203.01993
-
When do GANs replicate? On the choice of dataset size 23 Feb 2022 · 1 repository · arXiv:2202.11765
-
FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations 13 Feb 2022 · 0 repositories · arXiv:2202.06240
-
Third Time's the Charm? Image and Video Editing with StyleGAN3 31 Jan 2022 · 1 repository · arXiv:2201.13433
Tasks archive 2025-07-28
20 shown of 140 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 | 53 |
| Attribute | 20 |
| Generative Adversarial Network | 20 |
| Disentanglement | 13 |
| Face Generation | 13 |
| Image Manipulation | 13 |
| Diversity | 11 |
| Data Augmentation | 10 |
| Face Recognition | 10 |
| Conditional Image Generation | 7 |
| Translation | 7 |
| Domain Adaptation | 6 |
| Face Swapping | 6 |
| Image-to-Image Translation | 5 |
| Knowledge Distillation | 5 |
| Transfer Learning | 5 |
| Image Reconstruction | 4 |
| Segmentation | 4 |
| Semantic Segmentation | 4 |
| Style Transfer | 4 |
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