当前位置: X-MOL 学术Signal Process. Image Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Gaussian correction for adversarial learning of boundaries
Signal Processing: Image Communication ( IF 3.5 ) Pub Date : 2022-08-19 , DOI: 10.1016/j.image.2022.116841
Iti Chaturvedi , Chen Qian , Roy E. Welsch , Kishor Thapa , Erik Cambria

Social networking sites often monitor the response to brands, events and activities during personal chats or videos. Here, the facial expression of the speaker can be used for automatic ranking of products. However, manual classification of videos puts the identity of the speaker at risk. There is imminent danger of fake videos circulating that are generated using style transfer. In this paper, we target both these challenges by using an adversarial model that can segment a face from the background scenery and occlusions. The segmentation for a fake video will be of poor quality compared to a real video. Previous segmentation models could only be trained on a few objects and failed on scenic images with occlusions. Here we propose an image translator that learns the boundaries of objects during training using Gaussian correction. To determine the parameters of the Gaussian distribution we make use of a Lyapunov candidate function that converges to a global maximum. We apply the model to segmentation of faces and cars in photos. We also apply it to the task of style transfer to the background without affecting the foreground object. The proposed method outperforms baselines by over 20% on segmentation metrics such as IoU and BFScore.



中文翻译:

边界对抗学习的高斯校正

社交网站通常会在个人聊天或视频期间监控对品牌、事件和活动的响应。在这里,说话者的面部表情可以用于产品的自动排序。然而,视频的手动分类会使说话者的身份面临风险。使用风格转移生成的假视频传播的危险迫在眉睫。在本文中,我们通过使用可以从背景风景和遮挡中分割人脸的对抗模型来解决这两个挑战。与真实视频相比,假视频的分割质量较差。以前的分割模型只能在少数对象上进行训练,并且在有遮挡的风景图像上失败。在这里,我们提出了一种图像翻译器,它在训练期间使用高斯校正来学习对象的边界。为了确定高斯分布的参数,我们使用收敛到全局最大值的 Lyapunov 候选函数。我们将该模型应用于照片中人脸和汽车的分割。我们还将其应用于在不影响前景对象的情况下将样式转移到背景的任务。所提出的方法在 IoU 和 BFScore 等分割指标上优于基线 20% 以上。

更新日期:2022-08-19
down
wechat
bug