# CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital Images

Source: [CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital Images](<https://www.sota2.com/research/paper/68fa67c81e209131cea18534>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:22:05.587Z

Authors: Shunquan Tan, Weilong Wu, Zilong Shao, Qiushi Li, Bin Li, Jiwu Huang

Published: 2019-11-12T03:39:42.000Z

## Abstract

Over the past few years, detection performance improvements of deep-learning based steganalyzers have been usually achieved through structure expansion. However, excessive expanded structure results in huge computational cost, storage overheads, and consequently difficulty in training and deployment. In this paper we propose CALPA-NET, a ChAnneL-Pruning-Assisted deep residual network architecture search approach to shrink the network structure of existing vast, over-parameterized deep-learning based steganalyzers. We observe that the broad inverted-pyramid structure of existing deep-learning based steganalyzers might contradict the well-established model diversity oriented philosophy, and therefore is not suitable for steganalysis. Then a hybrid criterion combined with two network pruning schemes is introduced to adaptively shrink every involved convolutional layer in a data-driven manner. The resulting network architecture presents a slender bottleneck-like structure. We have conducted extensive experiments on BOSSBase+BOWS2 dataset, more diverse ALASKA dataset and even a large-scale subset extracted from ImageNet CLS-LOC dataset. The experimental results show that the model structure generated by our proposed CALPA-NET can achieve comparative performance with less than two percent of parameters and about one third FLOPs compared to the original steganalytic model. The new model possesses even better adaptivity, transferability, and scalability.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1911.04657>)

[PDF](<https://arxiv.org/pdf/1911.04657.pdf>)
