mlsanityData to 7 Oct 2026

Unpaired Image Translation via Vector Symbolic Architectures

arXiv 2209.02686 ↗First posted 6 Sep 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Image-to-image translation has played an important role in enabling synthetic data for computer vision. However, if the source and target domains have a large semantic mismatch, existing techniques often suffer from source content corruption aka semantic flipping. To address this problem, we propose a new paradigm for image-to-image translation using Vector Symbolic Architectures (VSA), a theoretical framework which defines algebraic operations in a high-dimensional vector (hypervector) space. We introduce VSA-based constraints on adversarial learning for source-to-target translations by learning a hypervector mapping that inverts the translation to ensure consistency with source content. We show both qualitatively and quantitatively that our method improves over other state-of-the-art techniques.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 36 of its 44 references that are in the map. First posted on arXiv 6 Sep 2022.

Builds on

36 of 44 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  8. 2018Demystifying MMD GANscited by 1,268
  9. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  10. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  11. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  12. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
24 more
  1. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  2. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  3. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  4. 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
  5. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  6. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  7. 2017Geometric GANcited by 232
  8. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  9. 2018Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mappingcited by 113
  10. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformationscited by 98
  11. 2017One-Sided Unsupervised Domain Mappingcited by 91
  12. 2018Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Datacited by 76
  13. 2021Enhancing Photorealism Enhancementcited by 74
  14. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challengescited by 68
  15. 2020A comparison of Vector Symbolic Architecturescited by 63
  16. 2020Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data Generationcited by 58
  17. 2021Hyperdimensional computing as a framework for systematic aggregation of image descriptorscited by 32
  18. 2020Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statisticscited by 15
  19. 2020Self-Supervised Real-to-Sim Scene Generationcited by 13
  20. 2015Properties of Sparse Distributed Representations and their Application to Hierarchical Temporal Memorycited by 12
  21. 2021Hyperseed: Unsupervised Learning with Vector Symbolic Architecturescited by 8
  22. 2016Encoding Data for HTM Systemscited by 6
  23. 2022Learning Temporally and Semantically Consistent Unpaired Video-to-video Translation Through Pseudo-Supervision From Synthetic Optical Flowcited by 5
  24. 2017Hyper-dimensional computing for a visual question-answering system that is trainable end-to-endcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 5; 2025: 1; 2026: 1.

13 papers.

Sort:

By area:

  1. 2023Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinementcited by 13
  2. 2024CARLA2Real: a tool for reducing the sim2real appearance gap in CARLA simulatorcited by 8
  3. 2024Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecturecited by 7
  4. 2024Synthetic to Authentic: Transferring Realism to 3D Face Renderings for Boosting Face Recognitioncited by 5
  5. 2023Towards Pragmatic Semantic Image Synthesis for Urban Scenescited by 4
  6. 2025AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognitioncited by 3
  7. 2023Hierarchy Flow For High-Fidelity Image-to-Image Translationcited by 2
  8. 2023Detecting Olives with Synthetic or Real Data? Olive the Abovecited by 2
  9. 2023Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translationcited by 2
  10. 2024Data Generation Scheme for Thermal Modality with Edge-Guided Adversarial Conditional Diffusion Modelcited by 1
  11. 2026HyPER-GAN: Hybrid Patch-Based Image-to-Image Translation for Real-Time Photorealism Enhancement in Game Enginescited by 1
  12. 2023SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignmentcited by 0
1 more
  1. 2024RoNet: Rotation-oriented Continuous Image Translationcited by 0