Back to Search
Start Over
Multi-Context Dual Hyper-Prior Neural Image Compression
- Publication Year :
- 2023
-
Abstract
- Transform and entropy models are the two core components in deep image compression neural networks. Most existing learning-based image compression methods utilize convolutional-based transform, which lacks the ability to model long-range dependencies, primarily due to the limited receptive field of the convolution operation. To address this limitation, we propose a Transformer-based nonlinear transform. This transform has the remarkable ability to efficiently capture both local and global information from the input image, leading to a more decorrelated latent representation. In addition, we introduce a novel entropy model that incorporates two different hyperpriors to model cross-channel and spatial dependencies of the latent representation. To further improve the entropy model, we add a global context that leverages distant relationships to predict the current latent more accurately. This global context employs a causal attention mechanism to extract long-range information in a content-dependent manner. Our experiments show that our proposed framework performs better than the state-of-the-art methods in terms of rate-distortion performance.<br />Comment: Accepted to IEEE 22$^nd$ International Conference on Machine Learning and Applications 2023 (ICMLA) - Selected for Oral Presentation
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2309.10799
- Document Type :
- Working Paper