W600k-r50.onnx | POPULAR |
WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition Authors: Zheng Zhu, Guan Huang, Jiankang Deng, et al. Venue: CVPR 2021
To use this .onnx file properly, you need to refer to (or cite) the following academic paper and technical documentation: Title: ArcFace: Additive Angular Margin Loss for Deep Face Recognition Authors: Jiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou Venue: CVPR 2019 (and TPAMI 2022) w600k-r50.onnx
Cite the InsightFace library as the software reference and the ArcFace paper as the algorithmic reference. Do not cite a paper specifically named "w600k-r50" – that is just a model filename. The w600k in the filename refers to a
The w600k in the filename refers to a WebFace600K training dataset, which was popularized by the ArcFace paper and the InsightFace repository. The ResNet50 architecture combined with the ArcFace loss is the standard backbone described in this work. The Dataset Paper: WebFace600K (or MS1MV3) The w600k likely refers to the WebFace600K dataset. If you are using the model as part of the standard InsightFace distribution (e.g., buffalo_l , antelope ), the official citation is: If you are using the model as part
Note: The w600k is a subset of WebFace260M (600k identities / 600 images each). If you use w600k-r50.onnx directly from the InsightFace model zoo, cite the InsightFace library :
@articleinsightface, title=InsightFace: 2D and 3D Face Alignment Library, author=Guo, Jia and Deng, Jiankang, journal=arXiv preprint arXiv:2107.07461, year=2021
The model name strongly suggests you are working with a face recognition model from the insightface library (specifically the Glint360K or WebFace600K trained ResNet50 model).
