# Semi-Supervised Building Footprint Generation with Feature and Output Consistency Training

arXiv: https://arxiv.org/abs/2205.08416 · HTML: https://mlsanity.com/paper/2205.08416/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 71 references that are in the map.
- First posted on arXiv 17 May 2022.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference](https://mlsanity.com/paper/1902.10421/) (2019)
- [Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation](https://mlsanity.com/paper/1805.04574/) (2018)
- [Deep learning in remote sensing: a review](https://mlsanity.com/paper/1710.03959/) (2017)
- [The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation](https://mlsanity.com/paper/1611.09326/) (2016)
- [There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average](https://mlsanity.com/paper/1806.05594/) (2018)
- [Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods](https://mlsanity.com/paper/1903.11260/) (2019)
- [Smooth Neighbors on Teacher Graphs for Semi-supervised Learning](https://mlsanity.com/paper/1711.00258/) (2017)
- [MAP-Net: Multi Attending Path Neural Network for Building Footprint Extraction from Remote Sensed Imagery](https://mlsanity.com/paper/1910.12060/) (2019)
- [Relation Network for Multi-label Aerial Image Classification](https://mlsanity.com/paper/1907.07274/) (2019)
- [Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks](https://mlsanity.com/paper/1709.05932/) (2017)
- [Building Footprint Generation by IntegratingConvolution Neural Network with Feature PairwiseConditional Random Field (FPCRF)](https://mlsanity.com/paper/2002.04600/) (2020)

## Built on by (most cited first, 5 of 5)

- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [PixelDINO: Semi-Supervised Semantic Segmentation for Detecting Permafrost Disturbances](https://mlsanity.com/paper/2401.09271/) (2024)
- [TSE-Net: Semi-supervised Monocular Height Estimation from Single Remote Sensing Images](https://mlsanity.com/paper/2511.13552/) (2025)
- [Building and Road Segmentation Using EffUNet and Transfer Learning Approach](https://mlsanity.com/paper/2307.03980/) (2023)
- [Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning](https://mlsanity.com/paper/2408.09460/) (2024)

## Abstract (arXiv)

Accurate and reliable building footprint maps are vital to urban planning and monitoring, and most existing approaches fall back on convolutional neural networks (CNNs) for building footprint generation. However, one limitation of these methods is that they require strong supervisory information from massive annotated samples for network learning. State-of-the-art semi-supervised semantic segmentation networks with consistency training can help to deal with this issue by leveraging a large amount of unlabeled data, which encourages the consistency of model output on data perturbation. Considering that rich information is also encoded in feature maps, we propose to integrate the consistency of both features and outputs in the end-to-end network training of unlabeled samples, enabling to impose additional constraints. Prior semi-supervised semantic segmentation networks have established the cluster assumption, in which the decision boundary should lie in the vicinity of low sample density. In this work, we observe that for building footprint generation, the low-density regions are more apparent at the intermediate feature representations within the encoder than the encoder's input or output. Therefore, we propose an instruction to assign the perturbation to the intermediate feature representations within the encoder, which considers the spatial resolution of input remote sensing imagery and the mean size of individual buildings in the study area. The proposed method is evaluated on three datasets with different resolutions: Planet dataset (3 m/pixel), Massachusetts dataset (1 m/pixel), and Inria dataset (0.3 m/pixel). Experimental results show that the proposed approach can well extract more complete building structures and alleviate omission errors.