An Adaptive Supervision Framework for Active Learning in Object Detection
This work addresses annotation cost reduction for object detection tasks, presenting an incremental improvement over existing active learning methods.
The paper tackles the problem of high annotation costs in active learning for object detection by proposing an adaptive supervision framework that queries weak labels first and increases supervision as needed, resulting in models trained with much lesser annotation costs than state-of-the-art approaches.
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.