Box-Level Active Detection

Mengyao Lyu1,2,3, Jundong Zhou1,2,3, Hui Chen1,2, Yijie Huang4, Dongdong Yu4, Yaqian Li4, Yandong Guo4, Yuchen Guo1,2, Liuyu Xiang5*, Guiguang Ding1,2*
1Tsinghua University, 2BNRist, 3Hangzhou Zhuoxi Institute of Brain and Intelligence, 4OPPO Research Institute, 5Beijing University of Posts and Telecommunications
*Corresponding Authors.

Abstract

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 BLAD.

BibTeX


      @article{lyu2023blad,
        title={Box-Level Active Detection},
        author={Lyu, Mengyao and Zhou, Jundong and Chen, Hui and Huang, Yijie and Yu, Dongdong and Li, Yaqian and Guo, Yandong and Guo, Yuchen and Xiang, Liuyu and Ding, Guiguang},
        booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
        pages={23766--23775},
        year={2023}
}