针对图像压缩模型提出结构化剪枝与量化，大幅减小模型体积且不损失压缩质量。
Structured Pruning and Quantization for Learned Image Compression
- 基于率失真损失设计层间剪枝比例，实现精准压缩
- 剪枝后模型尺寸更小，但率失真性能无下降（BD-Rate不变）
- 可与量化结合，进一步压缩模型，适合部署场景
大型深度学习模型的高计算成本严重制约其实际部署。尽管模型剪枝在图像分类和目标检测等任务中已被广泛研究，但在学习型图像压缩（LIC）中的应用仍有限。本文提出一种面向LIC模型的结构化剪枝方法，旨在降低图像压缩的计算开销，同时保持率失真性能。采用基于率失真损失的神经架构搜索（NAS）方法，确定网络各层的剪枝比例。将剪枝后的模型与同结构未压缩模型对比，结果表明模型尺寸显著减小，但无BD-Rate性能损失。进一步验证该剪枝方法可与模型量化结合，在维持相近BD-Rate表现的同时实现更大幅度的模型压缩。代码已开源至gitlab.com/viper-purdue/lic-pruning。
原文摘要 · Abstract (English)
The high computational costs associated with large deep learning models significantly hinder their practical deployment. Model pruning has been widely explored in deep learning literature to reduce their computational burden, but its application has been largely limited to computer vision tasks such as image classification and object detection. In this work, we propose a structured pruning method targeted for Learned Image Compression (LIC) models that aims to reduce the computational costs associated with image compression while maintaining the rate-distortion performance. We employ a Neural Architecture Search (NAS) method based on the rate-distortion loss for computing the pruning ratio for each layer of the network. We compare our pruned model with the uncompressed LIC Model with same network architecture and show that it can achieve model size reduction without any BD-Rate performance drop. We further show that our pruning method can be integrated with model quantization to achieve further model compression while maintaining similar BD-Rate performance. We have made the source code available at gitlab.com/viper-purdue/lic-pruning.
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。