Tag: CVPR 2021
-
Slimmable Compressive Autoencoders for Practical Neural Image Compression
Fei Yang, Luis Herranz, Yongmei Cheng, Mikhail G. Mozerov Read Full Paper → Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting their practical use. Focusing on practical image compression, we propose slimmable compressive autoencoders […]