An adaptive supervision framework for active learning in object detection

Desai, S.V. and Lagandula, A.C. and Guo, W. and Ninomiya, S. and Balasubramanian, Vineeth N (2020) An adaptive supervision framework for active learning in object detection. In: 30th British Machine Vision Conference, BMVC 2019, 9 September 2019through 12 September 2019, Cardiff.

Full text not available from this repository. (Request a copy)


Active learning approaches in computer vision generally involve querying strong labels for data. However, previous works have shown that weak supervision can be effective in training models for vision tasks while greatly reducing annotation costs. Using this knowledge, we propose an adaptive supervision framework for active learning and demonstrate its effectiveness on the task of object detection. Instead of directly querying bounding box annotations (strong labels) for the most informative samples, we first query weak labels and optimize the model. Using a switching condition, the required supervision level can be increased. Our framework requires little to no change in model architecture. Our extensive experiments show that the proposed framework can be used to train good generalizable models with much lesser annotation costs than the state of the art active learning approaches for object detection. © 2019. The copyright of this document resides with its authors.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Balasubramanian, Vineeth N
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Active Learning; Bounding box; Model architecture; State of the art; Switching conditions; Training model; Weak labels
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 25 Oct 2022 13:26
Last Modified: 25 Oct 2022 13:26
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 11048 Statistics for this ePrint Item