Training Robust Object Detectors From Noisy Category Labels and Imprecise Bounding Boxes.
- Publisher:
- Institute of Electrical and Electronics Engineers
- Publication Type:
- Journal Article
- Citation:
- IEEE Transactions on Image Processing, 2021, 30, pp. 5782-5792
- Issue Date:
- 2021
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Training_Robust_Object_Detectors_From_Noisy_Category_Labels_and_Imprecise_Bounding_Boxes.pdf | 3.34 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Object detection has gained great improvements with the advances of convolutional neural networks and the availability of large amounts of accurate training data. Though the amount of data is increasing significantly, the quality of data annotations is not guaranteed from the existing crowd-sourcing labeling platforms. In addition to noisy category labels, imprecise bounding box annotations are commonly existed for object detection data. When the quality of training data degenerates, the performance of the typical object detectors is severely impaired. In this paper, we propose a Meta-Refine-Net (MRNet) to train object detectors from noisy category labels and imprecise bounding boxes. First, MRNet learns to adaptively assign lower weights to proposals with incorrect labels so as to suppress large loss values generated by these proposals on the classification branch. Second, MRNet learns to dynamically generate more accurate bounding box annotations to overcome the misleading of imprecisely annotated bounding boxes. Thus, the imprecise bounding boxes could impose positive impacts on the regression branch rather than simply be ignored. Third, we propose to refine the imprecise bounding box annotations by jointly learning from both the category and the localization information. By doing this, the approximation of ground-truth bounding boxes is more accurate while the misleading would be further alleviated. Our MRNet is model-agnostic and is capable of learning from noisy object detection data with only a few clean examples (less than 2%). Extensive experiments on PASCAL VOC 2012 and MS COCO 2017 demonstrate the effectiveness and efficiency of our method.
Please use this identifier to cite or link to this item: