ALWOD: Active Learning for Weakly-Supervised Object Detection

TL;DR

ALWOD introduces a novel active learning framework that combines weakly and semi-supervised object detection, utilizing a new image generator, an uncertainty-based acquisition function, and human-in-the-loop labeling to improve detection with minimal labeled data.

Contribution

The paper presents a new ALWOD framework that effectively integrates active learning with weakly and semi-supervised object detection, including a warm-start strategy and a disagreement-based acquisition function.

Findings

Significantly reduces the gap between few-shot and fully supervised object detection.

Demonstrates strong performance across multiple challenging benchmarks.

Code is publicly available for reproducibility.

Abstract

Object detection (OD), a crucial vision task, remains challenged by the lack of large training datasets with precise object localization labels. In this work, we propose ALWOD, a new framework that addresses this problem by fusing active learning (AL) with weakly and semi-supervised object detection paradigms. Because the performance of AL critically depends on the model initialization, we propose a new auxiliary image generator strategy that utilizes an extremely small labeled set, coupled with a large weakly tagged set of images, as a warm-start for AL. We then propose a new AL acquisition function, another critical factor in AL success, that leverages the student-teacher OD pair disagreement and uncertainty to effectively propose the most informative images to annotate. Finally, to complete the AL loop, we introduce a new labeling task delegated to human annotators, based on selection and correction of model-proposed detections, which is both rapid and effective in labeling the informative images. We demonstrate, across several challenging benchmarks, that ALWOD significantly narrows the gap between the ODs trained on few partially labeled but strategically selected image instances and those that rely on the fully-labeled data. Our code is publicly available on https://github.com/seqam-lab/ALWOD.