mlsanityData to 7 Oct 2026

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

arXiv 2212.07593 ↗First posted 15 Dec 2022cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two limitations: lack of training emphasis and cascading errors from decoding sequence. We design and present Selective Query Recollection (SQR), a simple and effective training strategy for query-based object detectors. It cumulatively collects intermediate queries as decoding stages go deeper and selectively forwards the queries to the downstream stages aside from the sequential structure. Such-wise, SQR places training emphasis on later stages and allows later stages to work with intermediate queries from earlier stages directly. SQR can be easily plugged into various query-based object detectors and significantly enhances their performance while leaving the inference pipeline unchanged. As a result, we apply SQR on Adamixer, DAB-DETR, and Deformable-DETR across various settings (backbone, number of queries, schedule) and consistently brings 1.4-2.8 AP improvement.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 34 of its 39 references that are in the map. First posted on arXiv 15 Dec 2022.

Builds on

34 of 39 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2016Layer Normalizationcited by 5,579
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  12. 2015Fast R-CNNcited by 2,930
22 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  2. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  3. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  4. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  5. 2016Deep Networks with Stochastic Depthcited by 973
  6. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  7. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  8. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  9. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  10. 2021Conditional DETR for Fast Training Convergencecited by 422
  11. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 270
  12. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  13. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  14. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  15. 2020Probabilistic Anchor Assignment with IoU Prediction for Object Detectioncited by 150
  16. 2022DETRs with Hybrid Matchingcited by 149
  17. 2022AdaMixer: A Fast-Converging Query-Based Object Detectorcited by 78
  18. 2022Accelerating DETR Convergence via Semantic-Aligned Matchingcited by 58
  19. 2019Soft Anchor-Point Object Detectioncited by 42
  20. 2019FoveaBox: Beyond Anchor-based Object Detectorcited by 37
  21. 2022NMS Strikes Backcited by 33
  22. 2020Search What You Want: Barrier Panelty NAS for Mixed Precision Quantizationcited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 4; 2026: 3.

17 papers.

Sort:

By area:

  1. 2025DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perceptioncited by 33
  2. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  3. 2024Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Modelscited by 13
  4. 2024A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationshipscited by 11
  5. 2023Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformercited by 9
  6. 2025MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanismcited by 9
  7. 2025Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perceptioncited by 9
  8. 2023Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detectioncited by 8
  9. 2024RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detectioncited by 4
  10. 2026PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detectioncited by 3
  11. 2024Enhancing DETRs Variants through Improved Content Query and Similar Query Aggregationcited by 2
  12. 2023Decoupled DETR For Few-shot Object Detectioncited by 1
5 more
  1. 2024Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Expertscited by 1
  2. 2025High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagerycited by 1
  3. 2026Integrating Diverse Assignment Strategies into DETRscited by 1
  4. 2024Sustainable Self-evolution Adversarial Trainingcited by 0
  5. 2026Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinementcited by 0