Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification
This work addresses the challenge of noisy pseudo labels in semi-supervised object detection, which is important for reducing labeling costs in computer vision, though it appears incremental as it builds on existing semi-supervised detection methods.
The paper tackles the problem of noise from pseudo labels in semi-supervised object detection by proposing a method that quantifies region uncertainty to achieve noise-resistant learning, demonstrating extraordinary performance on PASCAL VOC and MS COCO datasets.
Semi-supervised learning aims to leverage a large amount of unlabeled data for performance boosting. Existing works primarily focus on image classification. In this paper, we delve into semi-supervised learning for object detection, where labeled data are more labor-intensive to collect. Current methods are easily distracted by noisy regions generated by pseudo labels. To combat the noisy labeling, we propose noise-resistant semi-supervised learning by quantifying the region uncertainty. We first investigate the adverse effects brought by different forms of noise associated with pseudo labels. Then we propose to quantify the uncertainty of regions by identifying the noise-resistant properties of regions over different strengths. By importing the region uncertainty quantification and promoting multipeak probability distribution output, we introduce uncertainty into training and further achieve noise-resistant learning. Experiments on both PASCAL VOC and MS COCO demonstrate the extraordinary performance of our method.