Current semi-supervised object detection (SSOD) algorithms typically assume
class balanced datasets (PASCAL VOC etc.) or slightly class imbalanced datasets
(MS-COCO, etc). This assumption can be easily violated since real world
datasets can be extremely class imbalanced in nature, thus making the
performance of semi-supervised object detectors far from satisfactory. Besides,
the research for this problem in SSOD is severely under-explored. To bridge
this research gap, we comprehensively study the class imbalance problem for
SSOD under more challenging scenarios, thus forming the first experimental
setting for class imbalanced SSOD (CI-SSOD). Moreover, we propose a simple yet
effective gradient-based sampling framework that tackles the class imbalance
problem from the perspective of two types of confirmation biases. To tackle
confirmation bias towards majority classes, the gradient-based reweighting and
gradient-based thresholding modules leverage the gradients from each class to
fully balance the influence of the majority and minority classes. To tackle the
confirmation bias from incorrect pseudo labels of minority classes, the
class-rebalancing sampling module resamples unlabeled data following the
guidance of the gradient-based reweighting module. Experiments on three
proposed sub-tasks, namely MS-COCO, MS-COCO to Object365 and LVIS, suggest that
our method outperforms current class imbalanced object detectors by clear
margins, serving as a baseline for future research in CI-SSOD. Code will be
available at this https URL

当前半监督目标检测算法通常假设类别平衡的数据集（如 PASCAL VOC 等）或类别稍不平衡的数据集（如 MS-COCO 等），然而真实世界的数据集往往具有极度的类别不平衡性，从而使半监督目标检测器的性能远远不令人满意。为了弥补这一研究空白，我们全面研究了半监督目标检测中类别不平衡问题的更具挑战性的场景，形成了第一个实验设置用于类别不平衡的半监督目标检测（CI-SSOD）。此外，我们提出了一个简单但有效的基于梯度的采样框架，从两个类型的确认偏差的角度解决了类别不平衡问题。实验结果表明，我们的方法在三个提出的子任务上，即 MS-COCO、MS-COCO 到 Object365 和 LVIS 上，均明显优于当前的类别不平衡目标检测器，为未来 CI-SSOD 研究提供了基准。