通过雅可比分析发现图像压缩自编码器的通用操作，可用于简化模型。
Discovering shared interpretable operations in image compression autoencoders
- 用雅可比分析探测无偏自编码器内部行为
- 发现可复用的共享操作，提升压缩效率
- 适合想简化复杂模型的研究者
随着深度学习在图像压缩等应用中的普及，尽管率失真权衡得到改善，但模型规模和透明度却持续下降。自编码器是该任务中最广泛使用的架构之一；然而，由于缺乏对其内部行为的清晰理解，这些模型往往趋向于更复杂的结构以获取性能提升。本文通过雅可比分析，探究无偏自编码器内部操作中是否存在普遍行为。若存在，这些行为可被提取，用于设计受复杂深度学习架构启发的低复杂度图像压缩模型。
原文摘要 · Abstract (English)
With the increasing adoption of deep learning for applications such as image compression, improvements in the rate-distortion trade-off have been achieved at the cost of increasingly larger and more opaque ''black-box'' models. Autoencoders are among the most widely used architectures for this task; however, without a clear understanding of their internal behavior, these models tend to grow in complexity to achieve more performance gains. In this paper, we investigate whether universal behaviors can be detected from the internal operations of bias-free autoencoders through Jacobian analysis. If such behaviors exist, they may be extracted to design low-complexity image compression models inspired by high-complexity deep learning architectures.
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。