SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints
This work addresses the problem of preventing tampered image misuse for social safety, presenting an incremental improvement through a novel framework.
The paper tackles the challenge of extracting comprehensive and accurate forgery clues in image forgery localization by introducing SUMI-IFL, an information-theoretic framework with sufficiency and minimality constraints, achieving superior performance over state-of-the-art methods in both in-dataset and cross-dataset comparisons.
Image forgery localization (IFL) is a crucial technique for preventing tampered image misuse and protecting social safety. However, due to the rapid development of image tampering technologies, extracting more comprehensive and accurate forgery clues remains an urgent challenge. To address these challenges, we introduce a novel information-theoretic IFL framework named SUMI-IFL that imposes sufficiency-view and minimality-view constraints on forgery feature representation. First, grounded in the theoretical analysis of mutual information, the sufficiency-view constraint is enforced on the feature extraction network to ensure that the latent forgery feature contains comprehensive forgery clues. Considering that forgery clues obtained from a single aspect alone may be incomplete, we construct the latent forgery feature by integrating several individual forgery features from multiple perspectives. Second, based on the information bottleneck, the minimality-view constraint is imposed on the feature reasoning network to achieve an accurate and concise forgery feature representation that counters the interference of task-unrelated features. Extensive experiments show the superior performance of SUMI-IFL to existing state-of-the-art methods, not only on in-dataset comparisons but also on cross-dataset comparisons.