OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild
OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild
复制标题
DOI：
10.1109/iccv48922.2021.00996
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Trung-Nghia Le;H. Nguyen;J. Yamagishi;I. Echizen
中科院分区：
文献类型：
--
作者：
Trung-Nghia Le;H. Nguyen;J. Yamagishi;I. Echizen
深度虚假媒体的泛滥引起了公众和相关部门的关注。针对社交媒体上的假脸，制定对策变得至关重要。本文对多面伪造检测和野外分割这两个新的对抗任务进行了全面的研究。在不受限制的自然场景中，在多张人脸中定位伪造人脸比传统的深度假人脸识别任务更具挑战性。为了促进这些新任务，我们创建了第一个大规模数据集，提出了高水平的挑战，该数据集被设计为面部识别丰富的注释，明确用于面部伪造检测和分割，即开放取证。由于其丰富的注释，我们的OpenForensics数据集在深度伪造预防和一般人脸检测方面都有很大的研究潜力。我们还为这些任务开发了一套基准，通过在各种场景下对我们新构建的数据集进行最先进的实例检测和分割方法的广泛评估。
The proliferation of deepfake media is raising concerns among the public and relevant authorities. It has become essential to develop countermeasures against forged faces in social media. This paper presents a comprehensive study on two new countermeasure tasks: multi-face forgery detection and segmentation in-the-wild. Localizing forged faces among multiple human faces in unrestricted natural scenes is far more challenging than the traditional deepfake recognition task. To promote these new tasks, we have created the first large-scale dataset posing a high level of challenges that is designed with face-wise rich annotations explicitly for face forgery detection and segmentation, namely Open-Forensics. With its rich annotations, our OpenForensics dataset has great potentials for research in both deepfake prevention and general human face detection. We have also developed a suite of benchmarks for these tasks by conducting an extensive evaluation of state-of-the-art instance detection and segmentation methods on our newly constructed dataset in various scenarios.