Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Generate, Segment and Refine: Towards Generic Manipulation Segmentation

About

Detecting manipulated images has become a significant emerging challenge. The advent of image sharing platforms and the easy availability of advanced photo editing software have resulted in a large quantities of manipulated images being shared on the internet. While the intent behind such manipulations varies widely, concerns on the spread of fake news and misinformation is growing. Current state of the art methods for detecting these manipulated images suffers from the lack of training data due to the laborious labeling process. We address this problem in this paper, for which we introduce a manipulated image generation process that creates true positives using currently available datasets. Drawing from traditional work on image blending, we propose a novel generator for creating such examples. In addition, we also propose to further create examples that force the algorithm to focus on boundary artifacts during training. Strong experimental results validate our proposal.

Peng Zhou, Bor-Chun Chen, Xintong Han, Mahyar Najibi, Abhinav Shrivastava, Ser Nam Lim, Larry S. Davis• 2018

Related benchmarks

TaskDatasetResultRank
Pixel-level Manipulation DetectionNIST
F1 Score45.6
34
Pixel-level Manipulation DetectionCOVER
F1 Score48.9
34
Pixel-level Manipulation DetectionColumbia
F1 Score62.2
34
Pixel-level Manipulation DetectionDEFACTO 12k
F1 Score37.9
32
Pixel-level Manipulation DetectionCASIA v1+
F1 Score57.4
22
Pixel-level Manipulation DetectionIMD
F1 Score68.7
20
Pixel-level Manipulation DetectionMEAN Across datasets
F1 Score53.4
20
Image-level manipulation detectionCASIA v1+
AUC0.5
19
Image Manipulation DetectionGeneral Inference Speed Evaluation Images
FPS31.7
16
Pixel-level Manipulation DetectionCASIA v1
F1 Score57.4
14
Showing 10 of 19 rows

Other info

Follow for update