Name
Title | ||
|---|---|---|
SCIDA: Self-Correction Integrated Domain Adaptation From Single- to Multi-Label Aerial Images |
Abstract | ||
|---|---|---|
Most publicly available datasets for image classification are with single labels, while images are inherently multilabeled in our daily life. Such an annotation gap makes many pretrained single-label classification models fail in practical scenarios. For aerial images, this annotation issue is more concerned: Aerial data naturally cover a relatively large land area with multiple labels, while annotated aerial datasets currently publicly available (e.g., UCM and AID) are single-labeled. As manually annotating multilabel aerial images (MAIs) would be time-/ labor-consuming, we propose a novel self-correction integrated domain adaptation (SCIDA) method for automatic multilabel learning. SCIDA is weakly supervised, i.e., automatically learning the multilabel image classification model from using massive, publicly available single-label images. To achieve this goal, we propose a novel labelwise self-correction (LWC) module to better explore underlying label correlations. This module also makes the unsupervised domain adaptation (UDA) from single-label to multilabel data possible. For model training, the proposed method uses single-label information yet requires no prior knowledge of multilabeled data and predicts labels for MAIs. Through extensive evaluations, the proposed model, which is trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, achieves much better performances than comparative methods on our collected multiscene aerial image dataset. The code and data are available on GitHub (https://github.com/Ryan315/Single2multi-DA). |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/TGRS.2022.3170357 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING |
Keywords | DocType | Volume |
Task analysis, Annotations, Training, Data models, Adaptation models, Correlation, Feature extraction, Aerial image, graph convolutional network (GCN), MAI dataset, noise, OpenStreetMap (OSM), unsupervised domain adaptation (UDA) | Journal | 60 |
ISSN | Citations | PageRank |
0196-2892 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tianze Yu | 1 | 0 | 1.01 |
| Jianzhe Lin | 2 | 0 | 1.69 |
| Lichao Mou | 3 | 254 | 25.35 |
| Yuansheng Hua | 4 | 16 | 5.96 |
| Xiao Xiang Zhu | 5 | 896 | 103.00 |
| Z. Jane Wang | 6 | 406 | 55.43 |