通过平衡采样提升小类目标检测，降低标注成本。
Box-Level Class-Balanced Sampling for Active Object Detection
- 按类别平衡采样，优先选少数类框标注。
- 在多个数据集上达到当前最优检测性能。
- 适合标注成本高、类别不均衡的检测场景。
深度目标检测模型训练需要昂贵的边界框标注。主动学习（AL）是一种可缓解标注负担的有前景技术。在目标检测中进行框级主动学习，即选择最富信息量的边界框进行标注，并用伪标签补充标注稀疏的图像，比整图标注更高效。我们发现，早期模型仅对多数类表现良好，导致伪标签严重类别不平衡。为此，提出一种类别平衡采样策略，优先选择少数类样本进行标注，使最终训练数据（主动学习获取的真实标签与伪标签）更类别均衡，从而训练出更优模型。同时提出任务感知的软伪标签策略，提升伪标签精度。在公开基准数据集上的实验表明，该方法达到当前最优性能。
原文摘要 · Abstract (English)
Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most informative boxes to label and supplementing the sparsely-labelled image with pseudo labels, has been shown to be more cost-effective than selecting and labelling the entire image. In box-level AL for object detection, we observe that models at early stage can only perform well on majority classes, making the pseudo labels severely class-imbalanced. We propose a class-balanced sampling strategy to select more objects from minority classes for labelling, so as to make the final training data, \ie, ground truth labels obtained by AL and pseudo labels, more class-balanced to train a better model. We also propose a task-aware soft pseudo labelling strategy to increase the accuracy of pseudo labels. We evaluate our method on public benchmarking datasets and show that our method achieves state-of-the-art performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。