Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection
This work addresses the high labeling costs in object detection for computer vision practitioners, offering a more efficient active learning approach that is not incremental but introduces a unified method to mitigate class bias.
The paper tackles the problem of reducing labeling costs for object detection by proposing an active learning framework that considers both uncertainty and robustness to avoid bias towards high-performing classes, achieving up to a 7.7% improvement in mAP or up to 82% reduction in labeling cost on datasets like PASCAL VOC and MS-COCO.
Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data. To reduce the labels dependency, various active learning strategies have been proposed, typically based on the confidence of the detector. However, these methods are biased towards high-performing classes and can lead to acquired datasets that are not good representatives of the testing set data. In this work, we propose a unified framework for active learning, that considers both the uncertainty and the robustness of the detector, ensuring that the network performs well in all classes. Furthermore, our method leverages auto-labeling to suppress a potential distribution drift while boosting the performance of the model. Experiments on PASCAL VOC07+12 and MS-COCO show that our method consistently outperforms a wide range of active learning methods, yielding up to a 7.7% improvement in mAP, or up to 82% reduction in labeling cost. Code will be released upon acceptance of the paper.