mlsanityData to 7 Oct 2026

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

arXiv 1904.07392 ↗First posted 16 Apr 2019cs.CV cs.LGcited by 289

Not on the map. Why?

Abstract (arXiv)

Current state-of-the-art convolutional architectures for object detection are manually designed. Here we aim to learn a better architecture of feature pyramid network for object detection. We adopt Neural Architecture Search and discover a new feature pyramid architecture in a novel scalable search space covering all cross-scale connections. The discovered architecture, named NAS-FPN, consists of a combination of top-down and bottom-up connections to fuse features across scales. NAS-FPN, combined with various backbone models in the RetinaNet framework, achieves better accuracy and latency tradeoff compared to state-of-the-art object detection models. NAS-FPN improves mobile detection accuracy by 2 AP compared to state-of-the-art SSDLite with MobileNetV2 model in [32] and achieves 48.3 AP which surpasses Mask R-CNN [10] detection accuracy with less computation time.

Key facts. Cited by 289 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 97; 2022: 63; 2023: 55; 2024: 33; 2025: 25; 2026: 15.

289 papers.

Sort:

By area:

  1. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  2. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  3. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  4. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  5. 2022Mixture-of-Experts with Expert Choice Routingcited by 611
  6. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  7. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  8. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  9. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  10. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  11. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  12. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
38 more
  1. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  2. 2021You Only Look One-level Featurecited by 116
  3. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 101
  4. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  5. 2021CAT: Cross Attention in Vision Transformercited by 92
  6. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  7. 2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
  8. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  9. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  10. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  11. 2025RF-DETR: Neural Architecture Search for Real-Time Detection Transformerscited by 70
  12. 2021PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Textcited by 65
  13. 2021Are we ready for a new paradigm shift? A Survey on Visual Deep MLPcited by 63
  14. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
  15. 2023YOLOv6 v3.0: A Full-Scale Reloadingcited by 58
  16. 2021Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusioncited by 56
  17. 2024HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstructioncited by 55
  18. 2023Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanismcited by 51
  19. 2023A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusioncited by 47
  20. 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Cloudscited by 45
  21. 2021Robust and Accurate Object Detection via Adversarial Learningcited by 42
  22. 2021HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformerscited by 39
  23. 2022DAMO-YOLO : A Report on Real-Time Object Detection Designcited by 38
  24. 2021AlphaNet: Improved Training of Supernets with Alpha-Divergencecited by 36
  25. 2023Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETRcited by 36
  26. 2023COCO-O: A Benchmark for Object Detectors under Natural Distribution Shiftscited by 34
  27. 2021Neural Architecture Search with Random Labelscited by 33
  28. 2021Contrastive Neural Architecture Search with Neural Architecture Comparatorscited by 33
  29. 2021A Review on Deep Learning in UAV Remote Sensingcited by 32
  30. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  31. 2022Reversible Column Networkscited by 32
  32. 2023Brainformers: Trading Simplicity for Efficiencycited by 31
  33. 2021PointFlow: Flowing Semantics Through Points for Aerial Image Segmentationcited by 29
  34. 2021Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Imagescited by 28
  35. 2021NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalizationcited by 28
  36. 2021Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Searchcited by 27
  37. 2021GAIA: A Transfer Learning System of Object Detection that Fits Your Needscited by 27
  38. 2021G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitationcited by 27

50 most cited of 289 All 289 (JSON)