Jin Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jin Wang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Jiajun Liang
Megvii Technology
2 shared publications - Renhe Ji
Technology
2 shared publications - Shichao Dong
Megvii Technology
2 shared publications Haoqiang Fan
Megvii Technology
1 shared publication- Haoqiang Fan
Megvii Technology, Beijing, China
1 shared publication - Zheng Ge
Megvii Technology
1 shared publication
Latest Publications
- Open Access
Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by the unexpected learned identity representation on images. Termed as the Implicit Identity Leakage, this phenomenon has been qualitatively and quantitatively verified among various DNNs. Furthermore, based on such understanding, we propose a simple yet effective method named the ID-unaware Deepfake Detection Model to reduce the influence of this phenomenon. Extensive experimental results demonstrate that our method outperforms the state-of-the-art in both in-dataset and cross-dataset evaluation. The code is available at https://github.com/megvii-research/CADDM.
Open AccessImplicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by the unexpected learned identity representation on images. Termed as the Implicit Identity Leakage, this phenomenon has been qualitatively and quantitatively verified among various DNNs. Furthermore, based on such understanding, we propose a simple yet effective method named the ID-unaware Deepfake Detection Model to reduce the influence of this phenomenon. Extensive experimental results demonstrate that our method outperforms the state-of-the-art in both in-dataset and cross-dataset evaluation. The code is available at https://github.com/megvii-research/CADDM.
- 23 October 2022
- Published by Springer Nature
- p. 18-35
Explaining Deepfake Detection by Analysing Image Matching
- 23 October 2022
- Published by Springer Nature
- p. 18-35
Explaining Deepfake Detection by Analysing Image Matching