Active learning selects informative samples for annotation within budget, which has proven efficient recently on object detection. However, the widely used active detection benchmarks conduct image-level evaluation, which is unrealistic in human workload estimation and biased towards crowded images. Furthermore, existing methods still perform image-level annotation, but equally scoring all targets within the same image incurs waste of budget and redundant labels. Having revealed above problems and limitations, we introduce a box-level active detection framework that controls a box-based budget per cycle, prioritizes informative targets and avoids redundancy for fair comparison and efficient application. Under the proposed box-level setting, we devise a novel pipeline, namely Complementary Pseudo Active Strategy (ComPAS). It exploits both human annotations and the model intelligence in a complementary fashion: an efficient input-end committee queries labels for informative objects only; meantime well-learned targets are identified by the model and compensated with pseudo-labels. ComPAS consistently outperforms 10 competitors under 4 settings in a unified codebase. With supervision from labeled data only, it achieves 100% supervised performance of VOC0712 with merely 19% box annotations. On the COCO dataset, it yields up to 4.3% mAP improvement over the second-best method. ComPAS also supports training with the unlabeled pool, where it surpasses 90% COCO supervised performance with 85% label reduction. Our source code is publicly available at https://github.com/lyumengyao/blad.

翻译：主动学习在预算限制下选择信息量大的样本进行标注，近年来在目标检测领域展现出高效性。然而，广泛使用的主动检测基准采用图像级评估，这在人工工作量估算上不切实际，且容易对密集图像产生偏差。此外，现有方法仍执行图像级标注，但对同一图像内的所有目标进行同等评分会导致预算浪费和标签冗余。针对上述问题与局限性，我们提出了一种框级主动检测框架，该框架每个周期控制基于框的预算，优先选择信息量大的目标并避免冗余，以实现公平比较与高效应用。在所提出的框级设置下，我们设计了一种新型流水线，即互补伪主动策略（ComPAS）。该策略以互补方式充分利用人工标注与模型智能：一个高效输入端委员会仅查询信息量大的对象的标签，同时由模型识别已充分学习的目标并用伪标签进行补偿。在统一代码库的4种设置下，ComPAS始终优于10种竞争方法。仅使用标注数据监督时，它仅用19%的框标注便达到了VOC0712数据集的100%监督性能。在COCO数据集上，其相比次优方法提升了高达4.3%的mAP。ComPAS还支持利用未标注池进行训练，在减少85%标签的情况下，其性能超过了90%的COCO监督任务表现。我们的源代码已公开于https://github.com/lyumengyao/blad。