Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
This addresses the challenge of effectively leveraging unlabeled data in object detection for computer vision applications, representing an incremental improvement over existing semi-supervised methods.
The paper tackles the problem of noise and overfitting in semi-supervised object detection by proposing a data-uncertainty guided multi-phase learning method, which improves performance by over 3% on PASCAL VOC and 2% on MS COCO compared to baselines.
In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models. Previous semi-supervised methods based on pseudo labels are severely degenerated by noise and prone to overfit to noisy labels, thus are deficient in learning different unlabeled knowledge well. To address this issue, we propose a data-uncertainty guided multi-phase learning method for semi-supervised object detection. We comprehensively consider divergent types of unlabeled images according to their difficulty levels, utilize them in different phases and ensemble models from different phases together to generate ultimate results. Image uncertainty guided easy data selection and region uncertainty guided RoI Re-weighting are involved in multi-phase learning and enable the detector to concentrate on more certain knowledge. Through extensive experiments on PASCAL VOC and MS COCO, we demonstrate that our method behaves extraordinarily compared to baseline approaches and outperforms them by a large margin, more than 3% on VOC and 2% on COCO.