# SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images

arXiv: https://arxiv.org/abs/2108.06810 · HTML: https://mlsanity.com/paper/2108.06810/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 57 references that are in the map.
- First posted on arXiv 15 Aug 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)
- [Learning a Deep ConvNet for Multi-label Classification with Partial Labels](https://mlsanity.com/paper/1902.09720/) (2019)
- [Progressive Identification of True Labels for Partial-Label Learning](https://mlsanity.com/paper/2002.08053/) (2020)
- [Partial Transfer Learning with Selective Adversarial Networks](https://mlsanity.com/paper/1707.07901/) (2017)
- [AutoDIAL: Automatic DomaIn Alignment Layers](https://mlsanity.com/paper/1704.08082/) (2017)
- [Multi-Label Classification with Label Graph Superimposing](https://mlsanity.com/paper/1911.09243/) (2019)
- [Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels](https://mlsanity.com/paper/1512.06974/) (2015)
- [Relation Network for Multi-label Aerial Image Classification](https://mlsanity.com/paper/1907.07274/) (2019)
- [Unsupervised Domain Adaptation Based on Source-guided Discrepancy](https://mlsanity.com/paper/1809.03839/) (2018)
- [Learning More Universal Representations for Transfer-Learning](https://mlsanity.com/paper/1712.09708/) (2017)
- [On the Power of Deep but Naive Partial Label Learning](https://mlsanity.com/paper/2010.11600/) (2020)

## Built on by (most cited first, 1 of 1)

- [Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification](https://mlsanity.com/paper/2109.02688/) (2021)

## Abstract (arXiv)

Most publicly available datasets for image classification are with single labels, while images are inherently multi-labeled in our daily life. Such an annotation gap makes many pre-trained single-label classification models fail in practical scenarios. This annotation issue is more concerned for aerial images: Aerial data collected from sensors naturally cover a relatively large land area with multiple labels, while annotated aerial datasets, which are publicly available (e.g., UCM, AID), are single-labeled. As manually annotating multi-label aerial images would be time/labor-consuming, we propose a novel self-correction integrated domain adaptation (SCIDA) method for automatic multi-label learning. SCIDA is weakly supervised, i.e., automatically learning the multi-label image classification model from using massive, publicly available single-label images. To achieve this goal, we propose a novel Label-Wise self-Correction (LWC) module to better explore underlying label correlations. This module also makes the unsupervised domain adaptation (UDA) from single- to multi-label data possible. For model training, the proposed model only uses single-label information yet requires no prior knowledge of multi-labeled data; and it predicts labels for multi-label aerial images. In our experiments, trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, the proposed model is tested directly on our collected Multi-scene Aerial Image (MAI) dataset.