|
我们真的需要收集数百万张人脸来进行有效的人脸识别吗?
Do We Really Need to Collect Millions of Faces for Effective Face Recognition? |
|
| |
| 课程网址: |
http://videolectures.net/eccv2016_masi_face_recognition/
|
| 主讲教师: |
Iacopo Masi
|
| 开课单位: |
南加州大学计算机科学系
|
| 开课时间: |
2016-10-24
|
| 课程语种: |
英语
|
| 中文简介: |
面部识别能力最近取得了惊人的飞跃。尽管这一进步至少部分归功于不断膨胀的训练集规模——大量的人脸图像被下载并标记为身份——但目前尚不清楚收集这么多图像的艰巨任务是否真的有必要。我们提出了一种更容易获得的方法来增加人脸识别系统的训练数据大小。而不是手动收集和标记更多的面孔，我们简单地合成它们。我们描述了通过操纵其包含的面部来丰富具有重要面部外观变化的现有数据集的新方法。在匹配使用标准卷积神经网络表示的查询图像时，我们进一步应用这种综合方法。在线性调频（LFW）和IJB-A(验证和识别)基准和Janus CS2上广泛测试了合成图像训练和测试的效果。通过我们的方法获得的性能与经过数百万下载图像训练的系统报告的最先进的结果相匹配。
|
| 课程简介: |
Face recognition capabilities have recently made extraordinary leaps. Though this progress is at least partially due to ballooning training set sizes -- huge numbers of face images downloaded and labeled for identity -- it is not clear if the formidable task of collecting so many images is truly necessary. We propose a far more accessible means of increasing training data sizes for face recognition systems. Rather than manually harvesting and labeling more faces, we simply synthesize them. We describe novel methods of enriching an existing dataset with important facial appearance variations by manipulating the faces it contains. We further apply this synthesis approach when matching query images represented using a standard convolutional neural network. The effect of training and testing with synthesized images is extensively tested on the LFW and IJB-A (verification and identification) benchmarks and Janus CS2. The performances obtained by our approach match state of the art results reported by systems trained on millions of downloaded images.
|
| 关 键 词: |
面部识别; 人脸识别; 训练数据
|
| 课程来源: |
视频讲座网
|
| 数据采集: |
2023-05-15：chenxin01
|
| 最后编审: |
2023-05-18：chenxin01
|
| 阅读次数: |
20
|
|
图 书 馆