Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection

TL;DR

This paper introduces a sandbox environment for rapid, transparent evaluation of active learning methods in deep object detection, significantly reducing computational costs and enabling faster research progress.

Contribution

It presents a new sandbox setup that allows quick and reliable testing of active learning strategies in deep object detection, improving comparability and efficiency.

Findings

Results in the sandbox are representative of standard configurations.

Compute time is reduced by up to 14 times on Pascal VOC.

Compute time is reduced by up to 32 times on BDD100k.

Abstract

Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire. Development of active learning methods in such fields is highly computationally expensive and time consuming which obstructs the progression of research and leads to a lack of comparability between methods. In this work, we propose and investigate a sandbox setup for rapid development and transparent evaluation of active learning in deep object detection. Our experiments with commonly used configurations of datasets and detection architectures found in the literature show that results obtained in our sandbox environment are representative of results on standard configurations. The total compute time to obtain results and assess the learning behavior can thereby be reduced by factors of up to 14 when comparing with Pascal VOC and up to 32 when comparing with BDD100k. This allows for testing and evaluating data acquisition and labeling strategies in under half a day and contributes to the transparency and development speed in the field of active learning for object detection.