Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)(2024)
摘要
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 https://github.com/nightkeepers/CI-SSOD.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要