An Adaptive Supervision Framework for Active Learning in Object Detection

TL;DR

This paper introduces an adaptive supervision framework for active learning in object detection that reduces annotation costs by initially using weak labels and switching to strong labels as needed, achieving comparable performance to state-of-the-art methods.

Contribution

It proposes a novel adaptive supervision framework that combines weak and strong labels in active learning for object detection, with minimal changes to existing models.

Findings

Significantly reduces annotation costs compared to existing methods.

Achieves comparable detection performance with less supervision.

Effective switching mechanism between weak and strong supervision.

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.