Towards Omni-Supervised Face Alignment for Large Scale Unlabeled Videos
نویسندگان
چکیده
منابع مشابه
Large-scale Supervised Hierarchical Feature Learning for Face Recognition
This paper proposes a novel face recognition algorithm based on large-scale supervised hierarchical feature learning. The approach consists of two parts: hierarchical feature learning and large-scale model learning. The hierarchical feature learning searches feature in three levels of granularity in a supervised way. First, face images are modeled by receptive field theory, and the representati...
متن کاملData Distillation: Towards Omni-Supervised Learning
We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lowerbounded by performance on existing labeled datasets, offering the potential to surpass state-of-the-art fully supervised methods. To exploit the omni-supervised setting, we p...
متن کاملExtended Supervised Descent Method for Robust Face Alignment
Supervised Descent Method (SDM) is a highly efficient and accurate approach for facial landmark locating/face alignment. It learns a sequence of descent directions that minimize the difference between the estimated shape and the ground truth in HOG feature space during training, and utilize them in testing to predict shape increment iteratively. In this paper, we propose to modify SDM in three ...
متن کاملSupplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
In this section, we present detailed network architecture as well as implementation details, for reproducible research. The network architecture for the reference network (RFNet) and video domain-adapted network (VDNet) are equivalent, as described in Table S1. The network architecture is mainly motivated from [8], but we replace ReLU with maxout units at every other convolution layer to furthe...
متن کاملLarge-Scale Semi-Supervised Learning
Labeling data is expensive, whilst unlabeled data is often abundant and cheap to collect. Semi-supervised learning algorithms that use both types of data can perform significantly better than supervised algorithms that use labeled data alone. However, for such gains to be observed, the amount of unlabeled data trained on should be relatively large. Therefore, making semi-supervised algorithms s...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i07.7011