Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.083923
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

BMGKD: A High Precision Object Detection Knowledge Distillation Method for Bridging Multi-Dimensional Gaps

Tianqi Wang, Yang Li, Zhisong Pan*
College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, China
* Corresponding Author: Zhisong Pan. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.083923

Received 13 April 2026; Accepted 09 June 2026; Published online 29 June 2026

Abstract

Existing knowledge distillation methods for object detection struggle to bridge the teacher-student capacity gap and overlook the inherent differences between classification and regression subtasks. To address these issues, we propose a Bridging Multi-dimensional Gaps Knowledge Distillation (BMGKD) method, which comprises two core modules: a feature difference distillation module and a response difference distillation module. The feature difference distillation module achieves global feature structural alignment via improved centered kernel alignment and performs local key feature alignment using joint spatial and channel-wise cosine similarity masks. The response difference distillation module constructs a dynamic classification mask and a high-quality prediction box selection mechanism, along with a classification and regression co-optimization loss function. On the MS COCO dataset, BMGKD achieves the highest mAP across all three teacher-student configurations on two-stage Faster R-CNN, single-stage anchor-free GFL, and single-stage anchor-based RetinaNet detectors. In the ResNet101→ResNet50 setting, it surpasses baselines by 2.7, 4.2, and 2.8 percentage points, respectively, and maintains consistent optimality under varying capacity gaps and cross-architecture scenarios. On Pascal VOC 2007, BMGKD attains mAP of 56.2%, 58.3%, and 58.0% on the same three detectors, outperforming all compared methods. Ablation studies confirm each component’s contribution. These results demonstrate that BMGKD effectively resolves the distillation accuracy degradation caused by capacity gaps and task discrepancies between teacher and student models. It provides an effective solution for knowledge distillation across diverse detection architectures.

Keywords

Object detection; knowledge distillation; model compression; feature fusion

  • 21

    View

  • 2

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link