paper-with-me

홈 › Papers

Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities

2024-07-29 · Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, Alessandro Nicolosi, Rita Cucchiara

Discerning between authentic content and that generated by advanced AI methods has become increasingly challenging. While previous research primarily addresses the detection of fake faces, the identification of generated natural images has only recently surfaced. This prompted the recent exploration of solutions that employ foundation vision-and-language models, like CLIP. However, the CLIP embedding space is optimized for global image-to-text alignment and is not inherently designed for deepfake detection, neglecting the potential benefits of tailored training and local image features. In this study, we propose CoDE (Contrastive Deepfake Embeddings), a novel embedding space specifically designed for deepfake detection. CoDE is trained via contrastive learning by additionally enforcing global-local similarities. To sustain the training of our model, we generate a comprehensive dataset that focuses on images generated by diffusion models and encompasses a collection of 9.2 million images produced by using four different generators. Experimental results demonstrate that CoDE achieves state-of-the-art accuracy on the newly collected dataset, while also showing excellent generalization capabilities to unseen image generators. Our source code, trained models, and collected dataset are publicly available at: https://github.com/aimagelab/CoDE.

📄 PDF Abstract BibTeX arXiv:2407.20337

Code (1)

aimagelab/code 공식 구현 pytorch

Tasks

Contrastive LearningDeepFake DetectionFace SwappingImage to text

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Contrastive Learning 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks

2025-11-09 · Yanan Zhao, Feng Ji, Jingyang Dai, Jiaze Ma 외 arxiv

Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically rely on fixed, handcrafted views-usually a local and a global perspective…

Contrastive Learning

Graph Representation Learning via Contrasting Cluster Assignments

2021-12-15 · ChunYang Zhang, Hongyu Yao, C. L. Philip Chen, Yuena Lin

With the rise of contrastive learning, unsupervised graph representation learning has been booming recently, even surpassing the supervised counterparts in some machine learning tasks. Most of existing contrastive models…

ClusteringContrastive LearningGraph Representation LearningRepresentation Learning

Multi-network Contrastive Learning Based on Global and Local Representations

2023-06-28 · Weiquan Li, Xianzhong Long, Yun Li

The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods…

Contrastive LearningLinear evaluationSelf-Supervised Learning

Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning

2023-06-23 · Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan

We propose ADCLR: A ccurate and D ense Contrastive Representation Learning, a novel self-supervised learning framework for learning accurate and dense vision representation. To extract spatial-sensitive information, ADCL…

Instance Segmentationobject-detectionObject DetectionRepresentation Learning+2

Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition

2023-02-05 · Binqian Xu, Xiangbo Shu

Contrastive learning has been successfully leveraged to learn action representations for addressing the problem of semi-supervised skeleton-based action recognition. However, most contrastive learning-based methods only …

Action RecognitionContrastive LearningSelf-Supervised Human Action RecognitionSkeleton Based Action Recognition