English

MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism

Computer Vision and Pattern Recognition 2025-03-04 v1

Abstract

Based on analyzing the character of cascaded decoder architecture commonly adopted in existing DETR-like models, this paper proposes a new decoder architecture. The cascaded decoder architecture constrains object queries to update in the cascaded direction, only enabling object queries to learn relatively-limited information from image features. However, the challenges for object detection in natural scenes (e.g., extremely-small, heavily-occluded, and confusingly mixed with the background) require an object detection model to fully utilize image features, which motivates us to propose a new decoder architecture with the parallel Multi-time Inquiries (MI) mechanism. MI enables object queries to learn more comprehensive information, and our MI based model, MI-DETR, outperforms all existing DETR-like models on COCO benchmark under different backbones and training epochs, achieving +2.3 AP and +0.6 AP improvements compared to the most representative model DINO and SOTA model Relation-DETR under ResNet-50 backbone. In addition, a series of diagnostic and visualization experiments demonstrate the effectiveness, rationality, and interpretability of MI.

Keywords

Cite

@article{arxiv.2503.01463,
  title  = {MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism},
  author = {Zhixiong Nan and Xianghong Li and Jifeng Dai and Tao Xiang},
  journal= {arXiv preprint arXiv:2503.01463},
  year   = {2025}
}

Comments

14 pages,9 figures,accepted to CVPR2025

R2 v1 2026-06-28T22:04:32.078Z