Progressive Self-Distillation for Ground-to-Aerial Perception Knowledge Transfer

by   Junjie Hu, et al.

We study a practical yet hasn't been explored problem: how a drone can perceive in an environment from viewpoints of different flight heights. Unlike autonomous driving where the perception is always conducted from a ground viewpoint, a flying drone may flexibly change its flight height due to specific tasks, requiring capability for viewpoint invariant perception. To reduce the effort of annotation of flight data, we consider a ground-to-aerial knowledge distillation method while using only labeled data of ground viewpoint and unlabeled data of flying viewpoints. To this end, we propose a progressive semi-supervised learning framework which has four core components: a dense viewpoint sampling strategy that splits the range of vertical flight height into a set of small pieces with evenly-distributed intervals, and at each height we sample data from that viewpoint; the nearest neighbor pseudo-labeling that infers labels of the nearest neighbor viewpoint with a model learned on the preceding viewpoint; MixView that generates augmented images among different viewpoints to alleviate viewpoint difference; and a progressive distillation strategy to gradually learn until reaching the maximum flying height. We collect a synthesized dataset and a real-world dataset, and we perform extensive experiments to show that our method yields promising results for different flight heights.


page 1

page 2

page 6

page 8

page 9


Progressive Representative Labeling for Deep Semi-Supervised Learning

Deep semi-supervised learning (SSL) has experienced significant attentio...

The Blackbird Dataset: A large-scale dataset for UAV perception in aggressive flight

The Blackbird unmanned aerial vehicle (UAV) dataset is a large-scale, ag...

SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite

The purpose of cross-view image matching is to match images acquired fro...

Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

We address the problem of learning new classes for semantic segmentation...

Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation

There is a growing interest in developing computer vision methods that c...

Towards Viewpoint Robustness in Bird's Eye View Segmentation

Autonomous vehicles (AV) require that neural networks used for perceptio...

Please sign up or login with your details

Forgot password? Click here to reset