ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Citations
16 citations
16 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...We first compare our IDGL using the state-of-the-art Light CNN (CNN-29 model) [65] and InsightFace [37] features, i.e., IDGL+LightCNN-29 and IDGL+InsightFace, with four recent deep learning-based methods, including DeepID [32], VGG-face [31], center loss-based CNN [34], and joint and collaborative representation with local adaptive convolution feature (JCR-ACF) [35], on the unconstrained LFW data set....
[...]
...The same situation applies to IDGL+InsightFace and NN+InsightFace....
[...]
...We first compare our IDGL using the state-of-the-art Light CNN (CNN-29 model) [65] and InsightFace [37] features, i....
[...]
...For reference, we also present the results of the nearest neighbor classier using the two deep learning-based features, i.e., NN+LightCNN-29 and NN+InsightFace....
[...]
...We also leverage the NN+LightCNN-29 and NN+InsightFace as two baseline methods....
[...]
16 citations
15 citations
Cites background from "ArcFace: Additive Angular Margin Lo..."
...For example, semantic landmark localization can be used to register correspondences between spatial positions and semantics (semantic alignment), which is extremely useful in many visual recognition tasks such as face recognition [8], [11] and person re-identification [12], [13]....
[...]
15 citations
References
123,388 citations
33,597 citations
30,843 citations
13,268 citations
10,447 citations