Transferable polychromatic optical encoder for neural networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911035625046016 |
|---|---|
| author | Choi, Minho Xiang, Jinlin Wirth-Singh, Anna Baek, Seung-Hwan Shlizerman, Eli Majumdar, Arka |
| author_facet | Choi, Minho Xiang, Jinlin Wirth-Singh, Anna Baek, Seung-Hwan Shlizerman, Eli Majumdar, Arka |
| contents | Artificial neural networks (ANNs) have fundamentally transformed the field of computer vision, providing unprecedented performance. However, these ANNs for image processing demand substantial computational resources, often hindering real-time operation. In this paper, we demonstrate an optical encoder that can perform convolution simultaneously in three color channels during the image capture, effectively implementing several initial convolutional layers of a ANN. Such an optical encoding results in ~24,000 times reduction in computational operations, with a state-of-the art classification accuracy (~73.2%) in free-space optical system. In addition, our analog optical encoder, trained for CIFAR-10 data, can be transferred to the ImageNet subset, High-10, without any modifications, and still exhibits moderate accuracy. Our results evidence the potential of hybrid optical/digital computer vision system in which the optical frontend can pre-process an ambient scene to reduce the energy and latency of the whole computer vision system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_02697 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transferable polychromatic optical encoder for neural networks Choi, Minho Xiang, Jinlin Wirth-Singh, Anna Baek, Seung-Hwan Shlizerman, Eli Majumdar, Arka Computer Vision and Pattern Recognition Optics Artificial neural networks (ANNs) have fundamentally transformed the field of computer vision, providing unprecedented performance. However, these ANNs for image processing demand substantial computational resources, often hindering real-time operation. In this paper, we demonstrate an optical encoder that can perform convolution simultaneously in three color channels during the image capture, effectively implementing several initial convolutional layers of a ANN. Such an optical encoding results in ~24,000 times reduction in computational operations, with a state-of-the art classification accuracy (~73.2%) in free-space optical system. In addition, our analog optical encoder, trained for CIFAR-10 data, can be transferred to the ImageNet subset, High-10, without any modifications, and still exhibits moderate accuracy. Our results evidence the potential of hybrid optical/digital computer vision system in which the optical frontend can pre-process an ambient scene to reduce the energy and latency of the whole computer vision system. |
| title | Transferable polychromatic optical encoder for neural networks |
| topic | Computer Vision and Pattern Recognition Optics |
| url | https://arxiv.org/abs/2411.02697 |