From db2db25f7e4cf178fe0094b72f7a6fcd7142fa7c Mon Sep 17 00:00:00 2001 From: Jia Guo Date: Thu, 24 Sep 2020 16:47:59 +0800 Subject: [PATCH] Update README.md --- IFRT/README.md | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/IFRT/README.md b/IFRT/README.md index 5eb5a6b..6640347 100644 --- a/IFRT/README.md +++ b/IFRT/README.md @@ -9,7 +9,15 @@ Submitting features is also allowed, you can send an e-mail to us to request the ## How to Participate -Send an e-mail to [..] after preparing your black-box feature extractor or image binary features. With your name, organization and submission comments. +Send an e-mail to [..] after preparing your black-box feature extractor or image binary features, with your name, organization and submission comments. + +There are some ways to submit: + +1. (Recommended) Submit black-box face feature extracting tool. +2. (Simplest) Submit your recognition model. + * Submit MXNet ArcFace model with the same face alignment. In this case, you can just submit the single model file. + * In other case, such as PyTorch/TF models or ArcFace models with different face alignment method, please give us an example on how to generate feature embeddings. (eg. provide a function `get_feature(image, landmark)`) +3. (Safe) Submit face features. We will give `N` test images named from `0.jpg` to `(N-1).jpg`. Then you should submit a binary feature file with shape `(N,K)` where `K` is your feature dimension. L2 distance will be used on these features. ## Leaderboard