Search Results for author:
Found 5 papers, 3 papers with code
Consistency and Accuracy of CelebA Attribute Values
Two annotators independently assigning attribute values shows that only 12 of 40 common attributes are assigned values with >= 95% consistency, and three (high cheekbones, pointed nose, oval face) have essentially random consistency.
Neural Generative Models for 3D Faces with Application in 3D Texture Free Face Recognition
Using heterogeneous depth cameras and 3D scanners in 3D face verification causes variations in the resolution of the 3D point clouds.
MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes
Unfortunately, it can be difficult to apply joint optimization to DCNNs when training data is imbalanced, and re-balancing multi-label data directly is structurally infeasible, since adding/removing data to balance one label will change the sampling of the other labels.
Towards Open Set Deep Networks
We present a methodology to adapt deep networks for open set recognition, by introducing a new model layer, OpenMax, which estimates the probability of an input being from an unknown class.
Towards Open World Recognition
We prove that thresholding sums of monotonically decreasing functions of distances in linearly transformed feature space can balance "open space risk" and empirical risk.
