mlsanityData to 7 Oct 2026

FCOS: Fully Convolutional One-Stage Object Detection

arXiv 1904.01355 ↗First posted 2 Apr 2019cs.CVcited by 1,573

Not on the map. Why?

Cited by 20 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with single-model and single-scale testing, surpassing previous one-stage detectors with the advantage of being much simpler. For the first time, we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Code is available at:Code is available at: https://tinyurl.com/FCOSv1

Key facts. Cited by 1,573 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 323; 2022: 400; 2023: 370; 2024: 245; 2025: 135; 2026: 100.

1,573 papers.

Sort:

By area:

  1. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  2. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  3. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  4. 2021Grounded Language-Image Pre-trainingcited by 1,147
  5. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  6. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  7. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 891
  8. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  9. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  12. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 612
38 more
  1. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  2. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  3. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  4. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  5. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  6. 2021Conditional DETR for Fast Training Convergencecited by 422
  7. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  8. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  9. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 345
  10. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  11. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  12. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 308
  13. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  14. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  15. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  16. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  17. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  18. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 236
  19. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  20. 2021Oriented R-CNN for Object Detectioncited by 230
  21. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  22. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  23. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  24. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  25. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  26. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  27. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  28. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  29. 2023ZipIt! Merging Models from Different Tasks without Trainingcited by 178
  30. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  31. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  32. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  33. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  34. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  35. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 159
  36. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  37. 2021Learning Salient Boundary Feature for Anchor-free Temporal Action Localizationcited by 156
  38. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155

50 most cited of 1,573 All 1,573 (JSON)