An Adaptive Supervision Framework for Active Learning in Object Detection

Sai Vikas Desai (Indian Institute of Technology, Hyderabad), Akshay Chandra Lagandula (Indian Institute Of Technology, Hyderabad), Wei Guo (The University of Tokyo), Seishi Ninomiya (The University of Tokyo), Vineeth N Balasubramanian (Indian Institute of Technology, Hyderabad)

Abstract
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.

DOI
10.5244/C.33.177
https://dx.doi.org/10.5244/C.33.177

Files
Paper (PDF)

BibTeX