Compressed Meta-Optical Encoder for Image Classification
Anna Wirth-Singh, Jinlin Xiang, Minho Choi, Johannes E. Fröch, Luocheng Huang, Eli Shlizerman, Arka Majumdar · 2024
For MNIST image classification, we compress a CNN to a single convolutional layer and linear electronic backend. We implement the convolution optically via engineering the PSF of meta-optics and demonstrate classification accuracy exceeding 93%.