# Portable Active Learning for Object Detection Source: [Portable Active Learning for Object Detection]() Collection index: [llms.txt]() Data updated: 2026-05-13T05:00:20.520Z Authors: Rashi Sharma, Justin Timothy C. Bersamin, Karthikk Subramanian Published: 2026-05-11T10:52:23.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on BDD (val)](): Object Detection; BDD (val); Round 1 Performance: 26.8. - [Object Detection on COCO](): Object Detection; COCO; AP (Box): not recorded. - [Object Detection on COCO (Percentage of additional annotations)](): Object Detection; COCO; Percentage of Additional Annotations: not recorded. - [Object Detection on PASCAL VOC (Annotation Percentage)](): Object Detection; Pascal VOC; Percentage of Additional Annotations: not recorded. ## Original sources and implementation [Original paper]() [PDF]()