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

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

3 Mar 2025CVPR 2025 1arXiv:2503.01463archive 2025-07-28

Zhixiong Nan, Xianghong Li, Jifeng Dai, Tao Xiang

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

CQU-ADHRI-Lab/MI-DETR officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO 2017 val MI-DETR (Swin-L 1x) AP 58.2 #3 of 33 Archive leaderboard report
Object Detection COCO 2017 val MI-DETR (Swin-L 1x) AP50 76.5 #3 of 33 Archive leaderboard report
Object Detection COCO 2017 val MI-DETR (Swin-L 1x) AP75 63.4 #3 of 33 Archive leaderboard report
Object Detection COCO 2017 val MI-DETR (Swin-L 1x) APL 74.6 #3 of 33 Archive leaderboard report
Object Detection COCO 2017 val MI-DETR (Swin-L 1x) APM 62.8 #3 of 33 Archive leaderboard report
Object Detection COCO 2017 val MI-DETR (Swin-L 1x) APS 42.5 #3 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionDINODense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections