Data Distillation, Face-Related Tasks, Multi Task Learning, Semi-Supervised Learning

by   Sepidehsadat Hosseini, et al.

We propose a new semi-supervised learning method on face-related tasks based on Multi-Task Learning (MTL) and data distillation. The proposed method exploits multiple datasets with different labels for different-but-related tasks such as simultaneous age, gender, race, facial expression estimation. Specifically, when there are only a few well-labeled data for a specific task among the multiple related ones, we exploit the labels of other related tasks in different domains. Our approach is composed of (1) a new MTL method which can deal with weakly labeled datasets and perform several tasks simultaneously, and (2) an MTL-based data distillation framework which enables network generalization for the training and test data from different domains. Experiments show that the proposed multi-task system performs each task better than the baseline single task. It is also demonstrated that using different domain datasets along with the main dataset can enhance network generalization and overcome the domain differences between datasets. Also, comparing data distillation both on the baseline and MTL framework, the latter shows more accurate predictions on unlabeled data from different domains. Furthermore, by proposing a new learning-rate optimization method, our proposed network is able to dynamically tune its learning rate.


page 3

page 4


Knowledge Assembly: Semi-Supervised Multi-Task Learning from Multiple Datasets with Disjoint Labels

In real-world scenarios we often need to perform multiple tasks simultan...

Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data

Deep learning-based models, when trained in a fully-supervised manner, c...

Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features

Multi-task learning (MTL) has received considerable attention, and numer...

A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysis

Affective Behavior Analysis is an important part in human-computer inter...

Multi-task Semi-supervised Learning for Pulmonary Lobe Segmentation

Pulmonary lobe segmentation is an important preprocessing task for the a...

Distillation based Multi-task Learning: A Candidate Generation Model for Improving Reading Duration

In feeds recommendation, the first step is candidate generation. Most of...

Please sign up or login with your details

Forgot password? Click here to reset