Unpaired Image-to-Image Translation for Segmentation and Signal Unmixing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915307106336768 |
|---|---|
| author | Andrejic, Nikola Spasic, Milica Mihajlovic, Igor Milosavljevic, Petra Pavlovic, Djordje Milisavljevic, Filip Milivojevic, Uros Delibasic, Danilo Mikic, Ivana Todorovic, Sinisa |
| author_facet | Andrejic, Nikola Spasic, Milica Mihajlovic, Igor Milosavljevic, Petra Pavlovic, Djordje Milisavljevic, Filip Milivojevic, Uros Delibasic, Danilo Mikic, Ivana Todorovic, Sinisa |
| contents | This work introduces Ui2i, a novel model for unpaired image-to-image translation, trained on content-wise unpaired datasets to enable style transfer across domains while preserving content. Building on CycleGAN, Ui2i incorporates key modifications to better disentangle content and style features, and preserve content integrity. Specifically, Ui2i employs U-Net-based generators with skip connections to propagate localized shallow features deep into the generator. Ui2i removes feature-based normalization layers from all modules and replaces them with approximate bidirectional spectral normalization -- a parameter-based alternative that enhances training stability. To further support content preservation, channel and spatial attention mechanisms are integrated into the generators. Training is facilitated through image scale augmentation. Evaluation on two biomedical tasks -- domain adaptation for nuclear segmentation in immunohistochemistry (IHC) images and unmixing of biological structures superimposed in single-channel immunofluorescence (IF) images -- demonstrates Ui2i's ability to preserve content fidelity in settings that demand more accurate structural preservation than typical translation tasks. To the best of our knowledge, Ui2i is the first approach capable of separating superimposed signals in IF images using real, unpaired training data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20746 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unpaired Image-to-Image Translation for Segmentation and Signal Unmixing Andrejic, Nikola Spasic, Milica Mihajlovic, Igor Milosavljevic, Petra Pavlovic, Djordje Milisavljevic, Filip Milivojevic, Uros Delibasic, Danilo Mikic, Ivana Todorovic, Sinisa Image and Video Processing Computer Vision and Pattern Recognition This work introduces Ui2i, a novel model for unpaired image-to-image translation, trained on content-wise unpaired datasets to enable style transfer across domains while preserving content. Building on CycleGAN, Ui2i incorporates key modifications to better disentangle content and style features, and preserve content integrity. Specifically, Ui2i employs U-Net-based generators with skip connections to propagate localized shallow features deep into the generator. Ui2i removes feature-based normalization layers from all modules and replaces them with approximate bidirectional spectral normalization -- a parameter-based alternative that enhances training stability. To further support content preservation, channel and spatial attention mechanisms are integrated into the generators. Training is facilitated through image scale augmentation. Evaluation on two biomedical tasks -- domain adaptation for nuclear segmentation in immunohistochemistry (IHC) images and unmixing of biological structures superimposed in single-channel immunofluorescence (IF) images -- demonstrates Ui2i's ability to preserve content fidelity in settings that demand more accurate structural preservation than typical translation tasks. To the best of our knowledge, Ui2i is the first approach capable of separating superimposed signals in IF images using real, unpaired training data. |
| title | Unpaired Image-to-Image Translation for Segmentation and Signal Unmixing |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.20746 |