Portable Active Learning for Object Detection

TL;DR

PAL is a detector-agnostic active learning framework that enhances object detection efficiency by combining instance uncertainty with image diversity, requiring no model modifications.

Contribution

Introduces PAL, a portable, inference-only active learning method that improves data selection for object detection without altering existing models or training procedures.

Findings

PAL outperforms existing active learning methods on COCO, PASCAL VOC, and BDD100K.

PAL improves label efficiency and detection accuracy.

PAL is compatible with various detectors and easy to deploy.

Abstract

Annotating bounding boxes is costly and limits the scalability of object detection. This challenge is compounded by the need to preserve high accuracy while minimizing manual effort in real-world applications. Prior active learning methods often depend on model features or modify detector internals and training schedules, increasing integration overhead. Moreover, they rarely jointly exploit the benefits of image-level signals, class-imbalance cues, and instance-level uncertainty for comprehensive selection. We present Portable Active Learning (PAL), a detector-agnostic, easily portable framework that operates solely on inference outputs. PAL combines class-wise instance uncertainty with image-level diversity to guide data selection. At each round, PAL trains lightweight class-specific logistic classifiers to distinguish true from false positives, producing entropy-based uncertainty scores for proposals. Candidate images are then refined using global image entropy, class diversity, and image similarity, yielding batches that are both informative and diverse. PAL requires no changes to model internals or training pipelines, ensuring broad compatibility across detectors. Extensive experiments on COCO, PASCAL VOC, and BDD100K demonstrate that PAL consistently improves label efficiency and detection accuracy compared to existing active learning baselines, making it a practical solution for scalable and cost-effective deployment of object detection in real-world settings.