REVIEW 6 cited by
IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Advanced image tampering techniques are increasingly challenging the trustworthiness of multimedia, leading to the development of Image Manipulation Localization (IML). But what makes a good IML model? The answer lies in the way to capture artifacts. Exploiting artifacts requires the model to extract non-semantic discrepancies between manipulated and authentic regions, necessitating explicit comparisons between the two areas. With the self-attention mechanism, naturally, the Transformer should be a better candidate to capture artifacts. However, due to limited datasets, there is currently no pure ViT-based approach for IML to serve as a benchmark, and CNNs dominate the entire task. Nevertheless, CNNs suffer from weak long-range and non-semantic modeling. To bridge this gap, based on the fact that artifacts are sensitive to image resolution, amplified under multi-scale features, and massive at the manipulation border, we formulate the answer to the former question as building a ViT with high-resolution capacity, multi-scale feature extraction capability, and manipulation edge supervision that could converge with a small amount of data. We term this simple but effective ViT paradigm IML-ViT, which has significant potential to become a new benchmark for IML. Extensive experiments on three different mainstream protocols verified our model outperforms the state-of-the-art manipulation localization methods. Code and models are available at https://github.com/SunnyHaze/IML-ViT.
Forward citations
Cited by 6 Pith papers
-
When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry
A geometry-aware forgery localizer (GFrame) that selectively fuses monocular depth and surface normals with RGB features outperforms 2D-only baselines on eight public manipulation benchmarks.
-
Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer
A sparse-attention vision transformer, trained without handcrafted feature extractors, reports state-of-the-art image manipulation localization and lower compute on four public benchmarks.
-
Progressive Decision-Making for Localizing Open-Ended AI-Generated Image Forgeries
A progressive evidence-guided Mamba state-update framework for image forgery localization outperforms one-shot predictors, especially on AI-generated forgeries.
-
VisGuard: Securing Visualization Dissemination through Tamper-Resistant Data Retrieval
A steganography pipeline keeps a 324-bit metadata link readable in visualization images after up to 60% local tampering or about 80% cropping.
-
Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection
A training-free nearest-neighbor detector built on CLIP intermediate features uses a small number of labeled examples from each new generator to classify deepfakes, reporting strong few-shot accuracy across three benchmarks.
-
Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems
A systematic review of deepfake detection finds a pervasive lack of adversarial robustness evaluation across all modalities and calls for resilient, modality-agnostic detectors.
Discussion (0). Continue with ORCID to comment.