Performance-guided Reinforced Active Learning for Object Detection

2026-01-22

AI Summary

This work addresses the limitation of existing active learning methods for object detection, which often fail to directly optimize task-specific performance metrics such as mean average precision (mAP), thereby constraining annotation efficiency. To overcome this, the authors propose MGRAL, a novel approach that, for the first time, employs mAP improvement as the reward signal in a reinforcement learning framework. By leveraging policy gradient methods, MGRAL optimizes batch sample selection strategies while effectively handling the combinatorial and non-differentiable nature of the problem. Additionally, an unsupervised, fast lookup mechanism is introduced to substantially reduce computational overhead. Evaluated on PASCAL VOC and COCO benchmarks, MGRAL achieves state-of-the-art active learning curves, significantly enhancing both model performance and labeling efficiency under identical annotation budgets, thus establishing a new paradigm for active learning in object detection.

Technology Category

• Machine Learning: Active Learning
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches to evaluating data informativeness predominantly focus on the data's distribution or intrinsic information content and do not directly correlate with downstream task performance, such as mean average precision (mAP) in object detection. Thus, we propose Performance-guided (i.e. mAP-guided) Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model output changes as informativeness. To address the combinatorial explosion challenge of batch sample selection and the non-differentiable correlation between model performance and selected batches, MGRAL skillfully employs a reinforcement learning-based sampling agent that optimizes selection using policy gradient with mAP improvement as reward. Moreover, to reduce the computational overhead of mAP estimation with unlabeled samples, MGRAL utilizes an unsupervised way with fast look-up tables, ensuring feasible deployment. We evaluate MGRAL's active learning performance on detection tasks over PASCAL VOC and COCO benchmarks. Our approach demonstrates the highest AL curve with convincing visualizations, establishing a new paradigm in reinforcement learning-driven active object detection.

Problem

• active learning
• object detection
• performance-guided
• informativeness
• mAP

Innovation

• performance-guided active learning
• reinforcement learning
• object detection
• mAP optimization
• unsupervised estimation