Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces

TL;DR

This paper introduces a Swin Transformer-based model for robust CGI image detection across multiple datasets and color spaces, demonstrating superior accuracy and domain generalization compared to CNN-based models.

Contribution

It proposes a novel Swin Transformer architecture tailored for CGI detection, leveraging hierarchical features and multi-color space analysis to improve robustness and generalization.

Findings

RGB color space yields highest accuracy

Swin Transformer outperforms CNN models like VGG-19 and ResNet-50

Model demonstrates strong intra- and inter-dataset robustness

Abstract

This study aims to address the growing challenge of distinguishing computer-generated imagery (CGI) from authentic digital images across three different color spaces; RGB, YCbCr, and HSV. Given the limitations of existing classification methods in handling the complexity and variability of CGI, this research proposes a Swin Transformer based model for accurate differentiation between natural and synthetic images. The proposed model leverages the Swin Transformer's hierarchical architecture to capture local and global features for distinguishing CGI from natural images. Its performance was assessed through intra- and inter-dataset testing across three datasets: CiFAKE, JSSSTU, and Columbia. The model was evaluated individually on each dataset (D1, D2, D3) and on the combined datasets (D1+D2+D3) to test its robustness and domain generalization. To address dataset imbalance, data augmentation techniques were applied. Additionally, t-SNE visualization was used to demonstrate the feature separability achieved by the Swin Transformer across the selected color spaces. The model's performance was tested across all color schemes, with the RGB color scheme yielding the highest accuracy for each dataset. As a result, RGB was selected for domain generalization analysis and compared with other CNN-based models, VGG-19 and ResNet-50. The comparative results demonstrate the proposed model's effectiveness in detecting CGI, highlighting its robustness and reliability in both intra-dataset and inter-dataset evaluations. The findings of this study highlight the Swin Transformer model's potential as an advanced tool for digital image forensics, particularly in distinguishing CGI from natural images. The model's strong performance indicates its capability for domain generalization, making it a valuable asset in scenarios requiring precise and reliable image classification.