Channel-wise wavelet-domain transformer attention plus wavelet-packet entropy modeling yields BD-rate reductions of 17.8-22.6% on Kodak, CLIC, and Tecnick relative to prior LIC baselines.
MambaVC: Learned visual compression with selective state spaces
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Deeper transformer layers produce intermediate representations that are harder to lossy-compress, and the paper links this to growing covariance and Rademacher complexity.
SAMIC introduces semantic-aware Mamba blocks and SVD-based redundancy reduction to achieve efficient perceptual image compression with improved rate-distortion-perception tradeoffs.
HCFSSNet uses convolutional layers plus a Vision Frequency State Space block with omni-directional scanning and frequency reweighting to reach competitive rate-distortion performance in learned image compression.
citing papers explorer
-
ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression
Channel-wise wavelet-domain transformer attention plus wavelet-packet entropy modeling yields BD-rate reductions of 17.8-22.6% on Kodak, CLIC, and Tecnick relative to prior LIC baselines.
-
Understanding Rate-Distortion Performance in Distributed Transformer Inference
Deeper transformer layers produce intermediate representations that are harder to lossy-compress, and the paper links this to growing covariance and Rademacher complexity.
-
SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression
SAMIC introduces semantic-aware Mamba blocks and SVD-based redundancy reduction to achieve efficient perceptual image compression with improved rate-distortion-perception tradeoffs.
-
A Compact Hybrid Convolution--Frequency State Space Network for Learned Image Compression
HCFSSNet uses convolutional layers plus a Vision Frequency State Space block with omni-directional scanning and frequency reweighting to reach competitive rate-distortion performance in learned image compression.