Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.087886
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

ReMiss: Missed-Object History for Data Scheduling in Driving-Scene Object Detection

Seongwook Lee1, Seungyeong Kim1, Jaemin Oh1, L. Minh Dang2, Hyeonjoon Moon3,*
1 Department of Convergence Engineering for Artificial Intelligence, Sejong University, Seoul, Republic of Korea
2 Ho Chi Minh City Open University, Ho Chi Minh City, Vietnam
5 Department of Computer Science and Engineering, Sejong University, Seoul, Republic of Korea
* Corresponding Author: Hyeonjoon Moon. Email: email
(This article belongs to the Special Issue: Novel Methods for Image Classification, Object Detection, and Segmentation, 2nd Edition)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.087886

Received 24 June 2026; Accepted 02 September 2026; Published online 20 September 2026

Abstract

Average precision (AP) is an aggregate detector metric and does not identify which annotated ground-truth instances remain unmatched across repeated evaluations during training. Existing hard example mining and sampling strategies usually define difficulty at the image, proposal, class, or loss level and do not retain recurrent object-level failures after post-processing as a data-scheduling signal. ReMiss uses missed-object history as a training-time data scheduling signal without changing detector architecture or loss. MissBank records each ground-truth instance’s miss status, miss-count history, and localization and confidence diagnostics. Hard Replay (HR) assigns priorities to full images containing currently missed objects based on miss counts and matching gaps, then schedules those images into later epochs under a replay budget. We evaluate ReMiss on KITTI, BDD100K, Cityscapes, and nuImages with fully convolutional one-stage object detection (FCOS), Faster R-CNN, and detection transformer with improved denoising anchor boxes (DINO), yielding 12 dataset–detector pairs. Across the full replay-ratio sweep, all 36 dataset–detector–ratio configurations improve upon the No-HR diagnostic baseline, with a minimum gain of +0.22 AP (sign test, p<10−10); under a replay ratio fixed in advance at 5.0%, all 12 pairs improve by +0.64–+2.17 AP. Selecting the HR setting by validation mean average precision (mAP), reported at mAP50:95, yields +1.03–+2.23 AP. These results support missed-object history as an architecture- and loss-agnostic scheduling signal across the evaluated detector families, with a measured 13%–27% increase in training time over the training-only baseline and no additional inference cost.

Keywords

Object detection; missed detection; ReMiss; MissBank; hard replay; hard example mining; autonomous driving; DINO

  • 26

    View

  • 6

    Download

  • 0

    Like

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

Share Link