Discovering shared interpretable operations in image compression autoencoders

2026-07-06

AI Summary

This work addresses the growing complexity and lack of interpretability in deep image compression autoencoder models, which hinder the design of efficient architectures. For the first time, it systematically employs Jacobian analysis to examine the internal transformations of unbiased autoencoders, uncovering consistent and interpretable operational patterns that are prevalent across high-dimensional compression models. Building on these insights, the study identifies multiple semantically meaningful internal operations shared across diverse models and demonstrates their utility in constructing lightweight architectures that simultaneously achieve high compression performance and low computational complexity. This approach establishes a new paradigm for designing interpretable and efficient compression models grounded in analytically derived internal mechanisms.

Abstract

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.

Problem

• image compression
• autoencoders
• interpretability
• Jacobian analysis
• universal behaviors

Innovation

• Jacobian analysis
• interpretable operations
• bias-free autoencoders
• image compression
• low-complexity models