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

TL;DR

The paper introduces SCIDA, a novel self-correction domain adaptation method that enables automatic multi-label aerial image classification using only single-label datasets, addressing annotation gaps in practical scenarios.

Contribution

It proposes a weakly supervised approach with a Label-Wise self-Correction module for domain adaptation from single- to multi-label aerial images, without requiring multi-label annotations.

Findings

Effective multi-label classification on aerial images

Successful domain adaptation from single- to multi-label data

Outperforms existing methods in experiments

Abstract

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.