Few-shot object detection (FSOD) is a challenging problem aimed at detecting novel concepts from few exemplars. Existing approaches to FSOD all assume abundant base labels to adapt to novel objects. This paper studies the new task of semi-supervised FSOD by considering a realistic scenario in which both base and novel labels are simultaneously scarce. We explore the utility of unlabeled data within our proposed label-efficient detection framework and discover its remarkable ability to boost semi-supervised FSOD by way of region proposals. Motivated by this finding, we introduce SoftER Teacher, a robust detector combining pseudo-labeling with consistency learning on region proposals, to harness unlabeled data for improved FSOD without relying on abundant labels. Rigorous experiments show that SoftER Teacher surpasses the novel performance of a strong supervised detector using only 10% of required base labels, without catastrophic forgetting observed in prior approaches. Our work also sheds light on a potential relationship between semi-supervised and few-shot detection suggesting that a stronger semi-supervised detector leads to a more effective few-shot detector.

翻译：少样本目标检测（FSOD）是一个具有挑战性的问题，旨在从少量样本中检测新概念。现有的FSOD方法均假设有充足的基础标签来适应新目标。本文研究半监督FSOD这一新任务，考虑基础和新型标签同时稀缺的现实场景。我们探索了无标签数据在所提出的标签高效检测框架中的效用，并发现其通过区域提议显著提升半监督FSOD的卓越能力。基于此发现，我们引入SoftER Teacher——一种将伪标签与区域提议一致性学习相结合的鲁棒检测器，以利用无标签数据改进FSOD，且无需依赖大量标签。严谨实验表明，SoftER Teacher仅使用10%所需基础标签即可超越强监督检测器的新类性能，且未出现先前方法中的灾难性遗忘。本研究还揭示了半监督与少样本检测之间的潜在关联：更强的半监督检测器能催生更有效的少样本检测器。