DeepAI AI Chat
Log In Sign Up

Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression

by   Wenshan Wang, et al.
Carnegie Mellon University

In the task of Autonomous aerial filming of a moving actor (e.g. a person or a vehicle), it is crucial to have a good heading direction estimation for the actor from the visual input. However, the models obtained in other similar tasks, such as pedestrian collision risk analysis and human-robot interaction, are very difficult to generalize to the aerial filming task, because of the difference in data distributions. Towards improving generalization with less amount of labeled data, this paper presents a semi-supervised algorithm for heading direction estimation problem. We utilize temporal continuity as the unsupervised signal to regularize the model and achieve better generalization ability. This semi-supervised algorithm is applied to both training and testing phases, which increases the testing performance by a large margin. We show that by leveraging unlabeled sequences, the amount of labeled data required can be significantly reduced. We also discuss several important details on improving the performance by balancing labeled and unlabeled loss, and making good combinations. Experimental results show that our approach robustly outputs the heading direction for different types of actor. The aesthetic value of the video is also improved in the aerial filming task.


page 1

page 2

page 4

page 5

page 6


Semi-Supervised Learning for Neural Keyphrase Generation

We study the problem of generating keyphrases that summarize the key poi...

MixMatch: A Holistic Approach to Semi-Supervised Learning

Semi-supervised learning has proven to be a powerful paradigm for levera...

How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?

This paper provides an exact characterization of the expected generaliza...

Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection

Deep learning demands a huge amount of well-labeled data to train the ne...

Semi-supervised Learning with Deterministic Labeling and Large Margin Projection

The centrality and diversity of the labeled data are very influential to...

Addressing Data Scarcity in Multimodal User State Recognition by Combining Semi-Supervised and Supervised Learning

Detecting mental states of human users is crucial for the development of...

Diverse Cotraining Makes Strong Semi-Supervised Segmentor

Deep co-training has been introduced to semi-supervised segmentation and...