mlsanityData to 14 Oct 2026

DSS-GAN: Directional State Space GAN with Mamba backbone for Class-Conditional Image Synthesis

arXiv 2603.17637 ↗First posted 18 Mar 2026cs.LG cs.CVcited by 0

On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models

Abstract (arXiv)

We present DSS-GAN, the first generative adversarial network to employ Mamba as a hierarchical generator backbone for noise-to-image synthesis. The central contribution is Directional Latent Routing (DLR), a novel conditioning mechanism that decomposes the latent vector into direction-specific subvectors, each jointly projected with a class embedding to produce a feature-wise affine modulation of the corresponding Mamba scan. Unlike conventional class conditioning that injects a global signal, DLR couples class identity and latent structure along distinct spatial axes of the feature map, applied consistently across all generative scales. DSS-GAN achieves improved FID, KID, and precision-recall scores compared to StyleGAN2-ADA across multiple tested datasets. Analysis of the latent space reveals that directional subvectors exhibit measurable specialization: perturbations along individual components produce structured, direction-correlated changes in the synthesized image.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 41 of its 50 references that are in the map. First posted on arXiv 18 Mar 2026.

Builds on

41 of 50 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026StyMam: A Mamba-Based Generator for Artistic Style Transfer19 Jan
  2. 2024DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation6 Nov
  3. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Model20 Mar

Other references · 38

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  8. 2017Neural Discrete Representation Learningcited by 4,712
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
26 more
  1. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  2. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  4. 2014Conditional Generative Adversarial Netscited by 2,162
  5. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  6. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  7. 2018Demystifying MMD GANscited by 1,293
  8. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  9. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  10. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  11. 2024VMamba: Visual State Space Modelcited by 969
  12. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  13. 2018Which Training Methods for GANs do actually Converge?cited by 679
  14. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  15. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  16. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  17. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  18. 2022Diffusion Models already have a Semantic Latent Spacecited by 328
  19. 2018cGANs with Projection Discriminatorcited by 254
  20. 2021ViTGAN: Training GANs with Vision Transformerscited by 110
  21. 2024CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulationcited by 35
  22. 2022f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformationcited by 32
  23. 2024I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingcited by 26
  24. 2024Rotate to Scan: UNet-like Mamba with Triplet SSM Module for Medical Image Segmentationcited by 12
  25. 2024Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiencycited by 9
  26. 2024GANs Conditioning Methods: A Surveycited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021Unsupervised Novel View Synthesis from a Single Image
  2. 2025Generative Adversarial Networks Bridging Art and Machine Intelligence
  3. 2023Unlocking Pre-trained Image Backbones for Semantic Image Synthesis
  4. 2026High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation
  5. 2023Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
  6. 2023FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits
  7. 2024Efficient generative adversarial networks using linear additive-attention Transformers
  8. 2021Content-Aware GAN Compression