Joint Graph Attention and Asymmetric Convolutional Neural Network for Deep Image Compression

Tang, Zhisen; Wang, Hanli; Yi, Xiaokai; Zhang, Yun; Kuo, C.-C. Jay

doi:10.1109/tcsvt.2022.3199472

Cited by 27 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2018). Later, deformable convolutions (Zhu et al 2019), octave convolutions (Chen, Xu, and Wang 2022), and asymmetric convolutions (Tang et al 2023) are developed to improve the standard convolutions. Recent works also introduce Transformers into CNNs (Liu, Sun, and Katto 2023).…”

Section: Introductionmentioning

confidence: 99%

Another Way to the Top: Exploit Contextual Clustering in Learned Image Coding

Zhang,

Duan,

et al. 2024

AAAI

View full text Add to dashboard Cite

While convolution and self-attention are extensively used in learned image compression (LIC) for transform coding, this paper proposes an alternative called Contextual Clustering based LIC (CLIC) which primarily relies on clustering operations and local attention for correlation characterization and compact representation of an image. As seen, CLIC expands the receptive field into the entire image for intra-cluster feature aggregation. Afterward, features are reordered to their original spatial positions to pass through the local attention units for inter-cluster embedding. Additionally, we introduce the Guided Post-Quantization Filtering (GuidedPQF) into CLIC, effectively mitigating the propagation and accumulation of quantization errors at the initial decoding stage. Extensive experiments demonstrate the superior performance of CLIC over state-of-the-art works: when optimized using MSE, it outperforms VVC by about 10% BD-Rate in three widely-used benchmark datasets; when optimized using MS-SSIM, it saves more than 50% BD-Rate over VVC. Our CLIC offers a new way to generate compact representations for image compression, which also provides a novel direction along the line of LIC development.

show abstract

Section: Introductionmentioning

confidence: 99%