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

11/12/2019
by   Shunquan Tan, et al.
0

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. By providing theoretical rationale, we demonstrate that the broad inverted-pyramid structure of existing deep-learning based steganalyzers contradicts the well-established model diversity oriented philosophy and 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 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 detection 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.

READ FULL TEXT

page 1

page 3

research
06/12/2022

STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor Decomposition

Recent studies shows that the majority of existing deep steganalysis mod...
research
12/07/2022

Slimmable Pruned Neural Networks

Slimmable Neural Networks (S-Net) is a novel network which enabled to se...
research
01/31/2021

AACP: Model Compression by Accurate and Automatic Channel Pruning

Channel pruning is formulated as a neural architecture search (NAS) prob...
research
05/23/2019

Network Pruning via Transformable Architecture Search

Network pruning reduces the computation costs of an over-parameterized n...
research
11/04/2020

DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search

The convolutional neural network has achieved great success in fulfillin...
research
02/26/2020

Automatically Searching for U-Net Image Translator Architecture

Image translators have been successfully applied to many important low l...
research
06/29/2020

The Heterogeneity Hypothesis: Finding Layer-Wise Dissimilated Network Architecture

In this paper, we tackle the problem of convolutional neural network des...

Please sign up or login with your details

Forgot password? Click here to reset