Face Analysis Project on MXNet
Ranked #1 on Face Alignment on IBUG
The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimize the label noise.
Ranked #1 on Face Verification on IJB-C (training dataset metric)
Face Analysis Project on MXNet
Ranked #3 on Face Detection on WIDER Face (Medium)
Face Analysis Project on MXNet
Ranked #5 on Lightweight Face Recognition on AgeDB-30
In this paper, we design a benchmark task and provide the associated datasets for recognizing face images and link them to corresponding entity keys in a knowledge base.
The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks.
Ranked #2 on Face Identification on MegaFace
In this workshop, we organize Masked Face Recognition (MFR) challenge and focus on bench-marking deep face recognition methods under the existence of facial masks.
Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection.
Ranked #1 on Face Parsing on Helen
Specifically, we reconstruct 3D face shape and reflectance from a large 2D facial dataset and introduce a novel method of transforming the VIS reflectance to NIR reflectance.
To close the gap between image domains, we create a large-scale dataset of diverse faces with gaze pseudo-annotations, which we extract based on the 3D geometry of the scene, and design a multi-view supervision framework to balance their effect during training.