Can I read Window-based Channel Attention for Wavelet-enhanced Learned Image Compression on EtoBox?

Window-based Channel Attention for Wavelet-enhanced Learned Image Compression by Xu, Heng; Hai, Bowen; Tang, Yushun; He, Zhihai is a scholarly article available to read on EtoBox.

What is Window-based Channel Attention for Wavelet-enhanced Learned Image Compression about?

Learned Image Compression (LIC) models have achieved superior rate-distortion performance than traditional codecs. Existing LIC models use CNN, Transformer, or Mixed CNN-Transformer as basic blocks. However, limited by the shifted window attention, Swin-Transformer-based LIC exhibits a restricted growth of receptive fields, affecting the ability to model large objects for image compression. To address this issue and improve the performance, we incorporate window partition into channel attention for the first time to obtain large receptive fields and capture more global information. Since channel attention hinders local information learning, it is important to extend existing attention mechanisms in Transformer codecs to the space-channel attention to establish multiple receptive fields, being able to capture global correlations with large receptive fields while maintaining detailed characterization of local correlations with small receptive fields. We also incorporate the discrete wavelet transform into our Spatial-Channel Hybrid (SCH) framework for efficient frequency-dependent down-sampling and further enlarging receptive fields. Experiment results demonstrate that our method ach

Author

Xu, Heng; Hai, Bowen; Tang, Yushun; He, Zhihai

Published

2024

Language

EN