Multiple Instance Active Learning for Object Detection

Tianning Yuan, Fang Wan, Mengying Fu, Jianzhuang Liu, Songcen Xu, Xiangyang Ji, Qixiang Ye; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 5330-5339


Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper, we propose Multiple Instance Active Object Detection (MI-AOD), to select the most informative images for detector training by observing instance-level uncertainty. MI-AOD defines an instance uncertainty learning module, which leverages the discrepancy of two adversarial instance classifiers trained on the labeled set to predict instance uncertainty of the unlabeled set. MI-AOD treats unlabeled images as instance bags and feature anchors in images as instances, and estimates the image uncertainty by re-weighting instances in a multiple instance learning (MIL) fashion. Iterative instance uncertainty learning and re-weighting facilitate suppressing noisy instances, toward bridging the gap between instance uncertainty and image-level uncertainty. Experiments validate that MI-AOD sets a solid baseline for instance-level active learning. On commonly used object detection datasets, MI-AOD outperforms state-of-the-art methods with significant margins, particularly when the labeled sets are small.

Related Material

[pdf] [arXiv]
@InProceedings{Yuan_2021_CVPR, author = {Yuan, Tianning and Wan, Fang and Fu, Mengying and Liu, Jianzhuang and Xu, Songcen and Ji, Xiangyang and Ye, Qixiang}, title = {Multiple Instance Active Learning for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {5330-5339} }