Syn2Real: Forgery Classification via Unsupervised Domain Adaptation
This addresses the challenge of insufficient public datasets for image forgery detection, particularly for copy-move forgeries, by enabling classification in cases where labeled data is unavailable, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles the problem of detecting copy-move forgeries in images by creating a synthetic dataset and using unsupervised domain adaptation to improve performance on realistic data, achieving F1 scores of 80.3% on CASIA and 78.8% on CoMoFoD datasets.
In recent years, image manipulation is becoming increasingly more accessible, yielding more natural-looking images, owing to the modern tools in image processing and computer vision techniques. The task of the identification of forged images has become very challenging. Amongst different types of forgeries, the cases of Copy-Move forgery are increasing manifold, due to the difficulties involved to detect this tampering. To tackle such problems, publicly available datasets are insufficient. In this paper, we propose to create a synthetic forged dataset using deep semantic image inpainting and copy-move forgery algorithm. However, models trained on these datasets have a significant drop in performance when tested on more realistic data. To alleviate this problem, we use unsupervised domain adaptation networks to detect copy-move forgery in new domains by mapping the feature space from our synthetically generated dataset. Furthermore, we improvised the F1 score on CASIA and CoMoFoD dataset to 80.3% and 78.8%, respectively. Our approach can be helpful in those cases where the classification of data is unavailable.