Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection
This work addresses the need for more efficient and effective semi-supervised object detection methods, offering a novel approach that improves upon existing pseudo-box-based techniques.
The paper tackled the problem of semi-supervised object detection by replacing sparse pseudo-boxes with dense pseudo-labels, which avoids post-processing and retains richer information, resulting in superior performance on COCO and VOC datasets under various settings.
To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the dense prediction as a united and straightforward form of pseudo-label. Compared to the pseudo-boxes, our Dense Pseudo-Label (DPL) does not involve any post-processing method, thus retaining richer information. We also introduce a region selection technique to highlight the key information while suppressing the noise carried by dense labels. We name our proposed SS-OD algorithm that leverages the DPL as Dense Teacher. On COCO and VOC, Dense Teacher shows superior performance under various settings compared with the pseudo-box-based methods.