利用特权信息增强目标检测：一种模型无关的师生框架方法

摘要

本文研究如何将特权信息学习范式整合到目标检测中，以利用训练阶段可用但推理阶段缺失的细粒度描述性信息。我们提出一种通用的、与模型无关的方法论，通过师生架构将边界框掩码、显著图及深度线索等特权信息注入基于深度学习的目标检测器。实验在五种先进目标检测模型及多个公共基准数据集上展开，包括基于无人机的垃圾检测数据集和Pascal VOC 2012，以评估其对精度、泛化能力和计算效率的影响。结果表明，经特权信息训练的学生模型始终优于基线模型，在未增加推理复杂度或模型参数量的前提下显著提升检测精度。该性能提升对中大型物体尤为显著，而消融实验表明教师指导的中间加权策略能最优平衡特权信息与标准输入的学习。研究证实特权信息学习框架为资源受限场景和实际应用中的目标检测系统提供了一种高效实用的改进策略。

English

This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection to exploit fine-grained, descriptive information available during training but not at inference. We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks, saliency maps, and depth cues-into deep learning-based object detectors through a teacher-student architecture. Experiments are conducted across five state-of-the-art object detection models and multiple public benchmarks, including UAV-based litter detection datasets and Pascal VOC 2012, to assess the impact on accuracy, generalization, and computational efficiency. Our results demonstrate that LUPI-trained students consistently outperform their baseline counterparts, achieving significant boosts in detection accuracy with no increase in inference complexity or model size. Performance improvements are especially marked for medium and large objects, while ablation studies reveal that intermediate weighting of teacher guidance optimally balances learning from privileged and standard inputs. The findings affirm that the LUPI framework provides an effective and practical strategy for advancing object detection systems in both resource-constrained and real-world settings.

利用特权信息增强目标检测：一种模型无关的师生框架方法

Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach

摘要

Support