用分层特征变换降低图像压缩模型复杂度，提升设备兼容性。
LoC-LIC: Low Complexity Learned Image Coding Using Hierarchical Feature Transforms
- 分层设计：高分辨率用少通道，低分辨率用多通道，均衡计算负载。
- 复杂度从1256 kMAC/Pixel降至270 kMAC/Pixel，性能基本不变。
- 适合移动端、嵌入式等算力受限场景的图像压缩应用。
当前学习型图像压缩模型通常计算复杂度较高，需要大量计算资源。为克服这一挑战，我们提出一种创新方法，通过分层特征提取变换显著降低复杂度，同时保持比特率压缩效率。新架构在高空间分辨率输入/特征图上使用较少通道，而在通道数较多的特征图上降低空间维度，从而有效减少计算负担，而不牺牲性能。该策略将前向传播复杂度从1256 kMAC/Pixel降低至仅270 kMAC/Pixel。因此，该低复杂度模型可使学习型图像压缩在多种设备上高效运行，并为图像压缩技术的新架构发展铺平道路。
原文摘要 · Abstract (English)
Current learned image compression models typically exhibit high complexity, which demands significant computational resources. To overcome these challenges, we propose an innovative approach that employs hierarchical feature extraction transforms to significantly reduce complexity while preserving bit rate reduction efficiency. Our novel architecture achieves this by using fewer channels for high spatial resolution inputs/feature maps. On the other hand, feature maps with a large number of channels have reduced spatial dimensions, thereby cutting down on computational load without sacrificing performance. This strategy effectively reduces the forward pass complexity from \(1256 \, \text{kMAC/Pixel}\) to just \(270 \, \text{kMAC/Pixel}\). As a result, the reduced complexity model can open the way for learned image compression models to operate efficiently across various devices and pave the way for the development of new architectures in image compression technology.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。