DeepID-implementation is an implementation of paper "Deep Learning Face Representation from Predicting 10,000 Classes", which proposes to learn a set of compact, 160-dims high level feature representations through deep learning, referred to as Deep hidden IDentity features (DeepID), for face verification.
More details in DeepID Notebook.
Dataset | People | Image | Size |
---|---|---|---|
CASIA-WebFace-custom | 10,575 | 392,304 | 62x62 |
LFW | 6,000 pairs | 62x62 |
Model | People | Training images | Validation images | Train | Test |
---|---|---|---|---|---|
62x62_3_e2_0264 | 264 | 9,554 | 939 | train | test |
62x62_3_e2_0528 | 528 | 16,076 | 1,544 | train | test |
62x62_3_e2_1057 | 1,057 | 37,977 | 3,686 | train | test |
62x62_3_e2_2115 | 2,115 | 72,126 | 6,978 | train | test |
62x62_3_e2_4230 | 4,230 | 143,939 | 13,977 | train | test |
62x62_3_e2_8460 | 8,460 | 284,466 | 27,498 | train | test |
62x62_3_e1_conventional | 8,460 | 284,466 | 27,498 | train | test |
- The classification ability of Multi-scale ConvNets
- The effectiveness of the learned hidden representations for face verification
- The learned features extract identity information
- Various face patches combination contributes to the performance
- Method comparison
with Joint Bayesian, Cosine Similarity, Euclidean Distance method.
Model | Joint Bayesian | Cosine Similarity | Euclidean Distance |
---|---|---|---|
62x62_3_e2_0264 | 0.61 | 0.735 | 0.6745 |
62x62_3_e2_0528 | 0.60 | 0.749333 | 0.701 |
62x62_3_e2_1057 | 0.61 | 0.758333 | 0.709167 |
62x62_3_e2_2115 | 0.65 | 0.778167 | 0.7365 |
62x62_3_e2_4230 | 0.66 | 0.793167 | 0.756833 |
62x62_3_e2_8460 | 0.66 | 0.7985 | 0.757 |
62x62_3_e1_conventional | 0.64 | 0.797667 | 0.763167 |
[1]. Yi Sun, Xiaogang Wang, Xiaoao Tang, Deep Learning Face Representation from Predicting 10,000 Classes, 2014-06-23
[2]. RiweiChen, Caffe实践-基于Caffe的人脸识别实现, 2015-11-01
[3]. RiweiChen, 深度学习论文笔记-Deep Learning Face Representation from Predicting 10,000 Classes, 2014-06-16
[4]. 張雨石, DeepID人脸识别算法之三代, 2014-12-23
[5]. RiweiChen, RiweiChen/DeepFace, 2016-04-14
[6]. Feng Wang, happynear/FaceVerification, 2016-04-25
[7]. Alfred Xiang Wu, AlfredXiangWu/face_verification_experiment, 2015-12-14