While the pseudo-label method has demonstrated considerable success in
semi-supervised object detection tasks, this paper uncovers notable limitations
within this approach. Specifically, the pseudo-label method tends to amplify
the inherent strengths of the detector while accentuating its weaknesses, which
is manifested in the missed detection of pseudo-labels, particularly for small
and tail category objects. To overcome these challenges, this paper proposes
Mixed Pseudo Labels (MixPL), consisting of Mixup and Mosaic for pseudo-labeled
data, to mitigate the negative impact of missed detections and balance the
model's learning across different object scales. Additionally, the model's
detection performance on tail categories is improved by resampling labeled data
with relevant instances. Notably, MixPL consistently improves the performance
of various detectors and obtains new state-of-the-art results with Faster
R-CNN, FCOS, and DINO on COCO-Standard and COCO-Full benchmarks. Furthermore,
MixPL also exhibits good scalability on large models, improving DINO Swin-L by
2.5% mAP and achieving nontrivial new records (60.2% mAP) on the COCO val2017
benchmark without extra annotations.

通过综合利用 Mixup、Mosaic 和有关实例重新采样有标签数据，本研究提出了 MixPL 方法改善伪标签方法在半监督目标检测任务中的局限性，尤其对小物体和尾部类别物体的伪标签检测，进一步提升了各种检测器的性能，创造了 Faster R-CNN、FCOS 和 DINO 在 COCO 标准和 COCO 完全数据集上的新的最优结果，且在大型模型上具有良好可扩展性，在没有额外注释的情况下，在 COCO val2017 数据集上取得了非平凡的新纪录（60.2% mAP）。