multi-patch aggregation models for resampling detection
This addresses a critical issue for forensic algorithms in handling diverse image sizes, though it is incremental as it builds on existing deep models.
The paper tackles the problem of resampling detection algorithms being sensitive to varying image dimensions, proposing a novel pooling strategy called ITERATIVE POOLING that dynamically adjusts input tensors, resulting in up to 7-8% improvement on public datasets compared to existing methods.
Images captured nowadays are of varying dimensions with smartphones and DSLR's allowing users to choose from a list of available image resolutions. It is therefore imperative for forensic algorithms such as resampling detection to scale well for images of varying dimensions. However, in our experiments, we observed that many state-of-the-art forensic algorithms are sensitive to image size and their performance quickly degenerates when operated on images of diverse dimensions despite re-training them using multiple image sizes. To handle this issue, we propose a novel pooling strategy called ITERATIVE POOLING. This pooling strategy can dynamically adjust input tensors in a discrete without much loss of information as in ROI Max-pooling. This pooling strategy can be used with any of the existing deep models and for demonstration purposes, we show its utility on Resnet-18 for the case of resampling detection a fundamental operation for any image sought of image manipulation. Compared to existing strategies and Max-pooling it gives up to 7-8% improvement on public datasets.