Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-6

Synthetic Image Detection

3260 papers • 126 benchmarks • 313 datasets

Identify if the image is real or generated/manipulated by any generative models (GAN or Diffusion).

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in synthetic-image-detection-6

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find synthetic-image-detection-6 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection

Keshigeyan Chandrasegaran, Ngai-Man Cheung, Ngoc-Trung Tran•Tue Mar 30 2021

This study meticulously constructs a counterexample space of high frequency spectral decay consistent CNN-generated images emerging from handcrafted experiments using DCGAN, LSGAN, WGAN-GP and StarGAN, and empirically shows that this frequency discrepancy can be avoided by a minor architecture change in the last upsampling operation.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Aggregating Layers for Deepfake Detection

S. Avidan, Amir Jevnisek•Sat Aug 20 2022

This work considers the case where the network is trained on one Deepfake algorithm, and tested on Deepfakes generated by another algorithm, so as to achieve SOTA results.

7 0

Paper Graph

Artifact: A Large-Scale Dataset With Artificial And Factual Images For Generalizable And Robust Synthetic Image Detection

Md Awsafur Rahman, Bishmoy Paul, Najibul Haque Sarker, Z. Hakim, S. Fattah•Wed Feb 22 2023

This paper presents a large-scale dataset named ArtiFact, comprising diverse generators, object categories, and real-world challenges, and proposes a multi-class classification scheme that addresses social platform impairments and effectively detects synthetic images from both seen and unseen generators.

47 0

Paper Graph

E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data

Aref Azizpour, Tai D. Nguyen, Manil Shrestha, Kaidi Xu, Edward Kim, Matthew C. Stamm•Thu Apr 11 2024

The Ensemble of Expert Embedders (E3) is introduced, a novel continual learning framework for updating synthetic image detectors that enables the accurate detection of images from newly emerged generators using minimal training data.

4 0

Paper Graph

Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis

Ohad Fried, Sergey Sinitsa•Sat Mar 18 2023

This work utilizes the architectural properties of convolutional neural networks (CNNs) to develop a new detection method that can detect images from a known generative model and enable us to establish relationships between fine-tuned generative models.

28 0

Paper Graph

Generalizable Synthetic Image Detection via Language-guided Contrastive Learning

Shile Zhang, Haiwei Wu, Jiantao Zhou•Mon May 22 2023

The proposed LanguAge-guided SynThEsis Detection (LASTED) model achieves much improved generalizability to unseen image generation models and delivers promising performance that far exceeds state-of-the-art competitors over four datasets.

46 0

Paper Graph

Adding a benchmark result helps the community track progress.

Synthetic Image Detection | State-of-the-Art