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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bartolo, Matthias, Seychell, Dylan, Hili, Gabriel, Montebello, Matthew, Debono, Carl James, Formosa, Saviour, Makantasis, Konstantinos
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911354955235328
author Bartolo, Matthias
Seychell, Dylan
Hili, Gabriel
Montebello, Matthew
Debono, Carl James
Formosa, Saviour
Makantasis, Konstantinos
author_facet Bartolo, Matthias
Seychell, Dylan
Hili, Gabriel
Montebello, Matthew
Debono, Carl James
Formosa, Saviour
Makantasis, Konstantinos
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02016
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach
Bartolo, Matthias
Seychell, Dylan
Hili, Gabriel
Montebello, Matthew
Debono, Carl James
Formosa, Saviour
Makantasis, Konstantinos
Computer Vision and Pattern Recognition
Artificial Intelligence
Emerging Technologies
Machine Learning
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.
title Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Emerging Technologies
Machine Learning
url https://arxiv.org/abs/2601.02016