all AI news
Theoretical Bound-Guided Hierarchical VAE for Neural Image Codecs
March 28, 2024, 4:42 a.m. | Yichi Zhang, Zhihao Duan, Yuning Huang, Fengqing Zhu
cs.LG updates on arXiv.org arxiv.org
Abstract: Recent studies reveal a significant theoretical link between variational autoencoders (VAEs) and rate-distortion theory, notably in utilizing VAEs to estimate the theoretical upper bound of the information rate-distortion function of images. Such estimated theoretical bounds substantially exceed the performance of existing neural image codecs (NICs). To narrow this gap, we propose a theoretical bound-guided hierarchical VAE (BG-VAE) for NIC. The proposed BG-VAE leverages the theoretical bound to guide the NIC model towards enhanced performance. We …
abstract arxiv autoencoders cs.lg eess.iv function hierarchical image images information narrow performance rate studies the information theory type vae variational autoencoders
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote