Shared Neural Space: Unified Precomputed Feature Encoding for Multi-Task and Cross Domain Vision
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916968014020608 |
|---|---|
| author | Li, Jing Bartosz, Oskar Wang, Chengyu Wnuczynski, Michal Godaliyadda, Dilshan Polley, Michael |
| author_facet | Li, Jing Bartosz, Oskar Wang, Chengyu Wnuczynski, Michal Godaliyadda, Dilshan Polley, Michael |
| contents | The majority of AI models in imaging and vision are customized to perform on specific high-precision task. However, this strategy is inefficient for applications with a series of modular tasks, since each requires a mapping into a disparate latent domain. To address this inefficiency, we proposed a universal Neural Space (NS), where an encoder-decoder framework pre-computes features across vision and imaging tasks. Our encoder learns transformation aware, generalizable representations, which enable multiple downstream AI modules to share the same feature space. This architecture reduces redundancy, improves generalization across domain shift, and establishes a foundation for effecient multi-task vision pipelines. Furthermore, as opposed to larger transformer backbones, our backbone is lightweight and CNN-based, allowing for wider across hardware. We furthur demonstrate that imaging and vision modules, such as demosaicing, denoising, depth estimation and semantic segmentation can be performed efficiently in the NS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20481 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Shared Neural Space: Unified Precomputed Feature Encoding for Multi-Task and Cross Domain Vision Li, Jing Bartosz, Oskar Wang, Chengyu Wnuczynski, Michal Godaliyadda, Dilshan Polley, Michael Computer Vision and Pattern Recognition Artificial Intelligence The majority of AI models in imaging and vision are customized to perform on specific high-precision task. However, this strategy is inefficient for applications with a series of modular tasks, since each requires a mapping into a disparate latent domain. To address this inefficiency, we proposed a universal Neural Space (NS), where an encoder-decoder framework pre-computes features across vision and imaging tasks. Our encoder learns transformation aware, generalizable representations, which enable multiple downstream AI modules to share the same feature space. This architecture reduces redundancy, improves generalization across domain shift, and establishes a foundation for effecient multi-task vision pipelines. Furthermore, as opposed to larger transformer backbones, our backbone is lightweight and CNN-based, allowing for wider across hardware. We furthur demonstrate that imaging and vision modules, such as demosaicing, denoising, depth estimation and semantic segmentation can be performed efficiently in the NS. |
| title | Shared Neural Space: Unified Precomputed Feature Encoding for Multi-Task and Cross Domain Vision |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.20481 |