no code implementations • 13 Jun 2017 • Md. Abul Hasnat, Julien Bohné, Jonathan Milgram, Stéphane Gentric, Liming Chen
Results show the effectiveness and excellent generalization ability of the proposed approach as it achieves state-of-the-art results on the LFW, YouTube faces and CACD datasets and competitive results on the IJB-A dataset.
no code implementations • 24 Mar 2017 • Abul Hasnat, Julien Bohné, Jonathan Milgram, Stéphane Gentric, Liming Chen
Although CNNs are mostly trained by optimizing the softmax loss, the recent trend shows an improvement of accuracy with different strategies, such as task-specific CNN learning with different loss functions, fine-tuning on target dataset, metric learning and concatenating features from multiple CNNs.
Ranked #6 on Age-Invariant Face Recognition on CACDVS