Multi-Scale Architectures Matter: On the Adversarial Robustness of Flow-based Lossless Compression
This work addresses the need for robust and efficient compression models in practical applications, but it appears incremental as it builds on existing flow-based methods.
The paper tackles the problem of adversarial robustness in flow-based lossless compression by analyzing multi-scale architectures, finding that they provide a shortcut that reduces computational complexity and prevents performance degradation with more layers, achieving the best trade-off between coding complexity and compression efficiency.
As a probabilistic modeling technique, the flow-based model has demonstrated remarkable potential in the field of lossless compression \cite{idf,idf++,lbb,ivpf,iflow},. Compared with other deep generative models (eg. Autoregressive, VAEs) \cite{bitswap,hilloc,pixelcnn++,pixelsnail} that explicitly model the data distribution probabilities, flow-based models perform better due to their excellent probability density estimation and satisfactory inference speed. In flow-based models, multi-scale architecture provides a shortcut from the shallow layer to the output layer, which significantly reduces the computational complexity and avoid performance degradation when adding more layers. This is essential for constructing an advanced flow-based learnable bijective mapping. Furthermore, the lightweight requirement of the model design in practical compression tasks suggests that flows with multi-scale architecture achieve the best trade-off between coding complexity and compression efficiency.