ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Citations
61 citations
Cites background from "ArcFace: Additive Angular Margin Lo..."
...Global faces based models usually accept whole faces as inputs [22, 34, 19, 28, 3]....
[...]
...global representations where whole faces are regarded as CNN inputs [22, 34, 19, 3]....
[...]
...To get a high-quality dataset, [3] refined the dataset and made it publicly available....
[...]
60 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...The effectiveness is assessed in terms of the comparative recognition performance of Arcface [15] trained on different datasets....
[...]
...For instance, the Arcface method trained by this new dataset outperforms stateof-the-art performance on the IJB-C by a notable margin....
[...]
...For the real data validation, we evaluate face recognition performance of ResNet [23] models trained on original and cleansed datasets by the Arcface loss [15]....
[...]
...In Table 4, adopting FaceScrub [37] as probe set and using the wash list provided by DeepInsight [15], the results of two MillionCelebs cleansed versions do not differ a lot, but they all outperform other training datasets by a large margin....
[...]
...Table 3: Cleanse 4 face recognition datasets and train deep models by Arcface [15] to test face verification accuracy (%)....
[...]
59 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...FairLoss Cos and FairLoss Arc represent the methods with our margin adaptive strategy used in CosFace [36] and ArcFace [5], respectively....
[...]
...The other is ResNet50 [10] with a modified structure, proposed in [5], after the last convolutional layer....
[...]
...We fix ‖xi‖ by L2 normalization and re-scale ‖xi‖ to s, following [20, 36, 5]....
[...]
...[5] directly add an angular margin in the angular space and have a more clear geometric interpretation....
[...]
...Corresponding Author tation, several large-margin loss functions have been proposed to improve the generalization ability of softmax loss, such as SphereFace [20], CosFace [36], and ArcFace [5]....
[...]
58 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...Specifically, our method achieves 95.54% average accuracy, about 0.4% average improvement over ArcFace....
[...]
...To the compared approaches, we compare the proposed method with the baseline Softmax loss and the recently popular state-of-the-arts, including SphereFace [18], CosFace [32] and ArcFace [4]....
[...]
...Recent years have witnessed remarkable progresses in face recognition, with a variety of approaches proposed in the literatures and applied in real applications [18, 32, 4, 7, 6, 42]....
[...]
...Recently, a variety of margin based softmax losses [18, 32, 4] have achieved the state-of-the-art performances....
[...]
...In particular, the proposed method surpasses the best approach ArcFace by an obvious margin (about 0.82% at Rank-1 identification rate and 0.68% verification rate)....
[...]
58 citations
References
123,388 citations
33,597 citations
30,843 citations
13,268 citations
10,447 citations