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

arXiv: https://arxiv.org/abs/2208.13404 · HTML: https://mlsanity.com/paper/2208.13404/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 29 Aug 2022.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [When2com: Multi-Agent Perception via Communication Graph Grouping](https://mlsanity.com/paper/2006.00176/) (2020)
- [Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries](https://mlsanity.com/paper/1803.08673/) (2018)
- [Who2com: Collaborative Perception via Learnable Handshake Communication](https://mlsanity.com/paper/2003.09575/) (2020)
- [Semi-Supervised Learning with Generative Adversarial Networks](https://mlsanity.com/paper/1606.01583/) (2016)
- [X-View: Graph-Based Semantic Multi-View Localization](https://mlsanity.com/paper/1709.09905/) (2017)
- [Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning](https://mlsanity.com/paper/1912.03227/) (2019)
- [LeafGAN: An Effective Data Augmentation Method for Practical Plant Disease Diagnosis](https://mlsanity.com/paper/2002.10100/) (2020)
- [Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment](https://mlsanity.com/paper/2010.09297/) (2020)
- [Improving Monocular Visual Odometry Using Learned Depth](https://mlsanity.com/paper/2204.01268/) (2022)
- [Boosting Light-Weight Depth Estimation Via Knowledge Distillation](https://mlsanity.com/paper/2105.06143/) (2021)
- [Efficient Object Detection Model for Real-Time UAV Applications](https://mlsanity.com/paper/1906.00786/) (2019)

## Abstract (arXiv)

We study a practical yet hasn't been explored problem: how a drone can perceive in an environment from 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 the capability for viewpoint invariant perception. Tackling the such problem with supervised learning will incur tremendous costs for data annotation of different flying heights. On the other hand, current semi-supervised learning methods are not effective under viewpoint differences. In this paper, we introduce the ground-to-aerial perception knowledge transfer and propose a progressive semi-supervised learning framework that enables drone perception using only labeled data of ground viewpoint and unlabeled data of flying viewpoints. Our framework has four core components: i) a dense viewpoint sampling strategy that splits the range of vertical flight height into a set of small pieces with evenly-distributed intervals, ii) nearest neighbor pseudo-labeling that infers labels of the nearest neighbor viewpoint with a model learned on the preceding viewpoint, iii) MixView that generates augmented images among different viewpoints to alleviate viewpoint differences, and iv) a progressive distillation strategy to gradually learn until reaching the maximum flying height. We collect a synthesized and a real-world dataset, and we perform extensive experimental analyses to show that our method yields 22.2% and 16.9% accuracy improvement for the synthesized dataset and the real world. Code and datasets are available on https://github.com/FreeformRobotics/Progressive-Self-Distillation-for-Ground-to-Aerial-Perception-Knowledge-Transfer.