mlsanityData to 14 Oct 2026

End-to-End Object Detection with Fully Convolutional Network

arXiv 2012.03544 ↗First posted 7 Dec 2020cs.CV cs.AIcited by 70

Not on the map. Why?

Abstract (arXiv)

Mainstream object detectors based on the fully convolutional network has achieved impressive performance. While most of them still need a hand-designed non-maximum suppression (NMS) post-processing, which impedes fully end-to-end training. In this paper, we give the analysis of discarding NMS, where the results reveal that a proper label assignment plays a crucial role. To this end, for fully convolutional detectors, we introduce a Prediction-aware One-To-One (POTO) label assignment for classification to enable end-to-end detection, which obtains comparable performance with NMS. Besides, a simple 3D Max Filtering (3DMF) is proposed to utilize the multi-scale features and improve the discriminability of convolutions in the local region. With these techniques, our end-to-end framework achieves competitive performance against many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets. The code is available at https://github.com/Megvii-BaseDetection/DeFCN .

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 18; 2022: 23; 2023: 17; 2024: 8; 2025: 4.

70 papers.

Sort:

By area:

  1. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  3. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  4. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  5. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
  6. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
  7. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 305
  8. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 248
  9. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  10. 2021Instances as Queriescited by 158
  11. 2022DETRs with Hybrid Matchingcited by 150
  12. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
38 more
  1. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 98
  2. 2022Rethinking Efficient Lane Detection via Curve Modelingcited by 88
  3. 2023Dense Distinct Query for End-to-End Object Detectioncited by 77
  4. 2022Sparse Instance Activation for Real-Time Instance Segmentationcited by 63
  5. 2021ISTR: End-to-End Instance Segmentation with Transformerscited by 52
  6. 2024Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidancecited by 46
  7. 2021Instance-Conditional Knowledge Distillation for Object Detectioncited by 42
  8. 2021Disentangle Your Dense Object Detectorcited by 37
  9. 2022Progressive End-to-End Object Detection in Crowded Scenescited by 31
  10. 2023Meta-Adapter: An Online Few-shot Learner for Vision-Language Modelcited by 31
  11. 2021Anchor DETR: Query Design for Transformer-Based Object Detectioncited by 30
  12. 2022DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detectioncited by 25
  13. 2021LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localizationcited by 24
  14. 2023Dynamic Grained Encoder for Vision Transformerscited by 24
  15. 2022ConQueR: Query Contrast Voxel-DETR for 3D Object Detectioncited by 21
  16. 2021IQDet: Instance-wise Quality Distribution Sampling for Object Detectioncited by 20
  17. 2021LGD: Label-guided Self-distillation for Object Detectioncited by 19
  18. 2022Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detectioncited by 19
  19. 2022Point2Seq: Detecting 3D Objects as Sequencescited by 15
  20. 2022Prediction-Guided Distillation for Dense Object Detectioncited by 14
  21. 2024GrootVL: Tree Topology is All You Need in State Space Modelcited by 13
  22. 2022You Should Look at All Objectscited by 12
  23. 2023BoxSnake: Polygonal Instance Segmentation with Box Supervisioncited by 12
  24. 2024Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detectioncited by 11
  25. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  26. 2022RF-Next: Efficient Receptive Field Search for Convolutional Neural Networkscited by 10
  27. 2025SuperRAG: Beyond RAG with Layout-Aware Graph Modelingcited by 9
  28. 2022PointScatter: Point Set Representation for Tubular Structure Extractioncited by 8
  29. 2022Consistency-Aware Anchor Pyramid Network for Crowd Localizationcited by 8
  30. 2023One-to-Few Label Assignment for End-to-End Dense Detectioncited by 8
  31. 2023FER-former: Multi-modal Transformer for Facial Expression Recognitioncited by 8
  32. 2021LLA: Loss-aware Label Assignment for Dense Pedestrian Detectioncited by 7
  33. 2021Object Detection Made Simpler by Eliminating Heuristic NMScited by 6
  34. 2022Fewer is More: Efficient Object Detection in Large Aerial Imagescited by 6
  35. 2022ISDA: Position-Aware Instance Segmentation with Deformable Attentioncited by 5
  36. 2023Deep Learning based Systems for Crater Detection: A Reviewcited by 5
  37. 2022What Are Expected Queries in End-to-End Object Detection?cited by 4
  38. 2022Featurized Query R-CNNcited by 4

50 most cited of 70 All 70 (JSON)