Sorry, you need to enable JavaScript to visit this website.

Multi-Patch Aggregation Models for Resampling Detection

Citation Author(s):
Mohit Lamba, Kaushik Mitra
Submitted by:
Mohit Lamba
Last updated:
16 May 2020 - 12:48am
Document Type:
Presentation Slides
Document Year:
Mohit Lamba
Paper Code:


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 two novel deep neural networks — Iterative Pooling Network (IPN), which does not
assume any prior information about the original image size, and Branched Network (BN), which uses this prior knowledge to produce better results. IPN adopts a novel iterative pooling strategy that converts tensors of multiple sizes to tensors of a fixed size, as required by deep learning models with fully connected layers. BN alternatively adopts a branched architecture with dedicated pathways for images of different sizes. The effectiveness of the proposed solution is demonstrated on two problems, resampling detection and photorealism detection, which are generally solved as independent problems with different deep learning models. The code is available at

0 users have voted:


Please find the code, ArXiv version and other details on this link


Presentation Slides for the project