Awesome

DLT-Height-Estimation.pytorch

Towards a comprehensive understanding of MHE networks, we propose to interpret them from multiple levels: 1) Neurons:unit-level dissection. Exploring the semantic and height selectivity of the learned internal deep representations; 2) Instances:object-level interpretation. Studying the effects of different semantic classes, scales and spatial contexts on height estimation; 3)Attribution: pixel-level analysis.

<div align="center"> <img src="resources/s1.png" width="800"/> </div> Fig. 1. MHE networks learn to recognize different semantic objects (road, building and tree) and height ranges implicitly. This figure shows thestrong selectivity of Transformer-based MHE networks on both the GTAH dataset and the real-world DFC 2019 dataset. (Best viewed with zoom in.) <div align="center"> <img src="resources/s2.png" width="800"/> </div> Fig. 2. Visualization of the high correlation between height ranges andfeature maps of MHE networks. (Best viewed with zoom in)

Introduction

License

This project is released under the Apache 2.0 license.