This page contains ResFace101: a ResNet-101 deep network model, tuned for face recognition.

We fine-tuned this model using the procedure described in _I. Masi*, A. Tran*, T. Hassner*, J. Leksut, G. Medioni, "Do We Really Need to Collect Million of Faces for Effective Face Recognition? "_, in Proc. of ECCV 2016 on the publicly available CASIA WebFace set.

Please, remember to cite our paper below, if you use our model, thanks.

latex<br/>@inproceedings{masi16dowe,<br/> title={Do {W}e {R}eally {N}eed to {C}ollect {M}illions of {F}aces <br/> for {E}ffective {F}ace {R}ecognition?},<br/> booktitle = {European Conference on Computer Vision},<br/> author={Iacopo Masi <br/> and Anh Tran <br/> and Tal Hassner <br/> and Jatuporn Toy Leksut <br/> and G'{e}rard Medioni},<br/> year={2016},<br/> }<br/>

[PDF]
[Webpage]

无链接