TransForensics: Image Forgery Localization with Dense Self-Attention
- URL: http://arxiv.org/abs/2108.03871v1
- Date: Mon, 9 Aug 2021 08:43:26 GMT
- Title: TransForensics: Image Forgery Localization with Dense Self-Attention
- Authors: Jing Hao and Zhixin Zhang and Shicai Yang and Di Xie and Shiliang Pu
- Abstract summary: We introduce TransForensics, a novel image forgery localization method inspired by Transformers.
The two major components in our framework are dense self-attention encoders and dense correction modules.
By conducting experiments on main benchmarks, we show that TransForensics outperforms the stateof-the-art methods by a large margin.
- Score: 37.2172540238706
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Nowadays advanced image editing tools and technical skills produce tampered
images more realistically, which can easily evade image forensic systems and
make authenticity verification of images more difficult. To tackle this
challenging problem, we introduce TransForensics, a novel image forgery
localization method inspired by Transformers. The two major components in our
framework are dense self-attention encoders and dense correction modules. The
former is to model global context and all pairwise interactions between local
patches at different scales, while the latter is used for improving the
transparency of the hidden layers and correcting the outputs from different
branches. Compared to previous traditional and deep learning methods,
TransForensics not only can capture discriminative representations and obtain
high-quality mask predictions but is also not limited by tampering types and
patch sequence orders. By conducting experiments on main benchmarks, we show
that TransForensics outperforms the stateof-the-art methods by a large margin.
Related papers
- Progressive Feedback-Enhanced Transformer for Image Forgery Localization [3.765051882812805]
We propose a Progressive FeedbACk-enhanced Transformer (ProFact) network to achieve coarse-to-fine image forgery localization.
We present an effective strategy to automatically generate large-scale forged image samples close to real-world forensic scenarios.
Our proposed localizer greatly outperforms the state-of-the-art on the ability and robustness of image forgery localization.
arXiv Detail & Related papers (2023-11-15T12:31:43Z) - Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust.
Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model.
We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
arXiv Detail & Related papers (2023-07-31T10:22:33Z) - MaskSketch: Unpaired Structure-guided Masked Image Generation [56.88038469743742]
MaskSketch is an image generation method that allows spatial conditioning of the generation result using a guiding sketch as an extra conditioning signal during sampling.
We show that intermediate self-attention maps of a masked generative transformer encode important structural information of the input image.
Our results show that MaskSketch achieves high image realism and fidelity to the guiding structure.
arXiv Detail & Related papers (2023-02-10T20:27:02Z) - TruFor: Leveraging all-round clues for trustworthy image forgery
detection and localization [17.270110456445806]
TruFor is a forensic framework that can be applied to a large variety of image manipulation methods.
We rely on the extraction of both high-level and low-level traces through a transformer-based fusion architecture.
Our method is able to reliably detect and localize both cheapfakes and deepfakes manipulations outperforming state-of-the-art works.
arXiv Detail & Related papers (2022-12-21T11:49:43Z) - Shrinking the Semantic Gap: Spatial Pooling of Local Moment Invariants
for Copy-Move Forgery Detection [7.460203098159187]
Copy-move forgery is a manipulation of copying and pasting specific patches from and to an image, with potentially illegal or unethical uses.
Recent advances in the forensic methods for copy-move forgery have shown increasing success in detection accuracy and robustness.
For images with high self-similarity or strong signal corruption, the existing algorithms often exhibit inefficient processes and unreliable results.
arXiv Detail & Related papers (2022-07-19T09:11:43Z) - Splicing Detection and Localization In Satellite Imagery Using
Conditional GANs [26.615687071827576]
We describe the use of a Conditional Generative Adversarial Network (cGAN) to identify spliced forgeries within satellite images.
Our method achieves high success on these detection and localization objectives.
arXiv Detail & Related papers (2022-05-03T22:25:48Z) - A Hierarchical Transformation-Discriminating Generative Model for Few
Shot Anomaly Detection [93.38607559281601]
We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image.
The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions.
arXiv Detail & Related papers (2021-04-29T17:49:48Z) - What makes fake images detectable? Understanding properties that
generalize [55.4211069143719]
Deep networks can still pick up on subtle artifacts in doctored images.
We seek to understand what properties of fake images make them detectable.
We show a technique to exaggerate these detectable properties.
arXiv Detail & Related papers (2020-08-24T17:50:28Z) - Swapping Autoencoder for Deep Image Manipulation [94.33114146172606]
We propose the Swapping Autoencoder, a deep model designed specifically for image manipulation.
The key idea is to encode an image with two independent components and enforce that any swapped combination maps to a realistic image.
Experiments on multiple datasets show that our model produces better results and is substantially more efficient compared to recent generative models.
arXiv Detail & Related papers (2020-07-01T17:59:57Z) - Learning Transformation-Aware Embeddings for Image Forensics [15.484408315588569]
Image Provenance Analysis aims at discovering relationships among different manipulated image versions that share content.
One of the main sub-problems for provenance analysis that has not yet been addressed directly is the edit ordering of images that share full content or are near-duplicates.
This paper introduces a novel deep learning-based approach to provide a plausible ordering to images that have been generated from a single image through transformations.
arXiv Detail & Related papers (2020-01-13T22:01:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.