Sub-center ArcFace: Boosting Face Recognition by Large-Scale Noisy Web Faces

294 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning Compatible Embeddings (2021, unknown): “52 φc ResNet50 Subcenter [8] MS1Mv0 95.”
Few-Shot Named Entity Recognition: A Comprehensive Study (2020, methodology): “To resolve such issue, we follow (Deng et al., 2020) and extend our method to a version called Multi-Prototype , by creating K/ 5 prototypes for each type given K examples per type.”
The SpeakIn System for VoxCeleb Speaker Recognition Challange 2021 (2021, methodology): “First, the subcenter method [22] was introduced to reduce the influence of possible noisy samples.”
SphereFace Revived: Unifying Hyperspherical Face Recognition (2021, background): “As a major line of research in deep FR, hyperspherical FR [2], [3], [4], [5], [9], [10], [26], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46] has become increasingly popular in recent years due to its effectiveness.”
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition (2021, background): “Even though growing efforts have been devoted to investigating sophisticated networks [9, 80, 8, 71, 16] and losses [32, 68, 66, 12, 27, 55, 10], academia is restricted by limited training set and nearly saturated test protocols.”