MIAdapt: Source-free Few-shot Domain Adaptive Object Detection for Microscopic Images
This addresses domain adaptation challenges in medical imaging where data collection is difficult and privacy constraints limit source data availability, though it appears incremental as it builds on existing source-free and few-shot methods.
The paper tackles the problem of object detection in microscopic images without access to source data and with limited target data, proposing MIAdapt, which outperforms state-of-the-art methods by +21.3% mAP on source-free UDA and +4.7% mAP on few-shot domain adaptation on the Raabin-WBC dataset.
Existing generic unsupervised domain adaptation approaches require access to both a large labeled source dataset and a sufficient unlabeled target dataset during adaptation. However, collecting a large dataset, even if unlabeled, is a challenging and expensive endeavor, especially in medical imaging. In addition, constraints such as privacy issues can result in cases where source data is unavailable. Taking in consideration these challenges, we propose MIAdapt, an adaptive approach for Microscopic Imagery Adaptation as a solution for Source-free Few-shot Domain Adaptive Object detection (SF-FSDA). We also define two competitive baselines (1) Faster-FreeShot and (2) MT-FreeShot. Extensive experiments on the challenging M5-Malaria and Raabin-WBC datasets validate the effectiveness of MIAdapt. Without using any image from the source domain MIAdapt surpasses state-of-the-art source-free UDA (SF-UDA) methods by +21.3% mAP and few-shot domain adaptation (FSDA) approaches by +4.7% mAP on Raabin-WBC. Our code and models will be publicly available.