mlsanityData to 7 Oct 2026

Feature Pyramid Networks for Object Detection

arXiv 1612.03144 ↗First posted 9 Dec 2016cs.CVcited by 5,021

Not on the map. Why?

Cited by 74 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant improvement as a generic feature extractor in several applications. Using FPN in a basic Faster R-CNN system, our method achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles, surpassing all existing single-model entries including those from the COCO 2016 challenge winners. In addition, our method can run at 5 FPS on a GPU and thus is a practical and accurate solution to multi-scale object detection. Code will be made publicly available.

Key facts. Cited by 5,021 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1027; 2022: 1073; 2023: 1081; 2024: 800; 2025: 617; 2026: 423.

5,021 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  4. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  6. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  8. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  9. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  10. 2021Transformers in Vision: A Surveycited by 1,009
  11. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  12. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
38 more
  1. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  2. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  3. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  4. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  5. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  6. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  7. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  8. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  9. 2021Transformer in Transformercited by 632
  10. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  11. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  12. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  13. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  14. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  15. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  16. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 481
  17. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  18. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  19. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 471
  20. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  21. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 435
  22. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  23. 2021Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysiscited by 418
  24. 2021Deep Long-Tailed Learning: A Surveycited by 416
  25. 2022Decoupled Knowledge Distillationcited by 380
  26. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
  27. 2021GAN Inversion: A Surveycited by 366
  28. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  29. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  30. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  31. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 354
  32. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 347
  33. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 345
  34. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  35. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  36. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  37. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  38. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310

50 most cited of 5,021 All 5,021 (JSON)