Workshops Archive

Lightweight CNN-Based Artifact Reduction for Scientific Error-bounded Lossy Compression

Workshop: The 11th International Workshop on Data Analysis and Reduction for Big Scientific Data

Authors: Zizhe Jian (University of California, Riverside); Pu Jiao (University of Kentucky); Bohan Zhang (University of Florida); Sheng Di (Argonne National Laboratory (ANL)); Xin Liang (University of Kentucky); Guanpeng Li (University of Florida); Huangliang Dai and Zizhong Chen (University of California, Riverside); and Franck Cappello (Argonne National Laboratory (ANL))

Abstract: Lossy compression is widely used to reduce storage and transmission costs in large-scale scientific data, but it inevitably introduces artifacts that may compromise subsequent analysis. To address this issue, we propose a lightweight 3D convolutional architecture with a fixed-scale batch normalization strategy, ensuring stable training and fast inference. We further analyze the trade-offs related to network size and highlight an empirical relationship between the minimum achievable MSE loss and the corresponding training cost. We also validate the generalizability of the network.

Experimental results on five representative scientific lossy compressors and datasets from four diverse scientific domains demonstrate that our method consistently improves reconstruction quality: MSE is reduced by one to four orders of magnitude, while keeping the inference time comparable to the compression runtime. A network trained on a single file generalizes well to other files within the same data set.

Back to The 11th International Workshop on Data Analysis and Reduction for Big Scientific Data Archive Listing Back to Full Workshop Archive Listing