Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection

TL;DR

This paper introduces a unified active learning framework for object detection that balances uncertainty and robustness, reducing labeling costs and improving performance across classes.

Contribution

It proposes a novel active learning approach that considers both uncertainty and robustness, and uses auto-labeling to mitigate distribution drift in object detection.

Findings

Outperforms existing active learning methods on PASCAL VOC and MS-COCO datasets.

Achieves up to 7.7% improvement in mAP over baseline methods.

Reduces labeling costs by up to 82%.

Abstract

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.