Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningAllobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Disentangling and Operationalizing AI Fairness at LinkedIn
Operationalizing AI fairness at LinkedIn's scale is challenging not only because there are multiple mutually incompatible definitions of fairness but also because determining what is fair depends on the specifics and con…
FairnessPseudoSeg: Designing Pseudo Labels for Semantic Segmentation
Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to…
Data Augmentationimage-classificationImage ClassificationSegmentation+2Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in real-world applications: 1) only limited labels are available for model trai…
DiagnosticDomain AdaptationUnsupervised Domain AdaptationReducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning
Labeling datasets is a noteworthy challenge in machine learning, both in terms of cost and time. This research, however, leverages an efficient answer. By exploring label propagation in semi-supervised learning, we can s…
Sentiment Analysistext-classificationText ClassificationRobust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy
Data pruning, which aims to downsize a large training set into a small informative subset, is crucial for reducing the enormous computational costs of modern deep learning. Though large-scale data collections invariably …