mlsanityData to 7 Oct 2026

EfficientDet: Scalable and Efficient Object Detection

arXiv 1911.09070 ↗First posted 20 Nov 2019cs.CV cs.LG eess.IVcited by 1,018

Not on the map. Why?

Abstract (arXiv)

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency. First, we propose a weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multiscale feature fusion; Second, we propose a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time. Based on these optimizations and better backbones, we have developed a new family of object detectors, called EfficientDet, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with single model and single-scale, our EfficientDet-D7 achieves state-of-the-art 55.1 AP on COCO test-dev with 77M parameters and 410B FLOPs, being 4x - 9x smaller and using 13x - 42x fewer FLOPs than previous detectors. Code is available at https://github.com/google/automl/tree/master/efficientdet.

Key facts. Cited by 1,018 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 234; 2022: 251; 2023: 191; 2024: 147; 2025: 124; 2026: 71.

1,018 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  3. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  4. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  5. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  6. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  7. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  8. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  9. 2021A White Paper on Neural Network Quantizationcited by 453
  10. 2021Pay Attention to MLPscited by 367
  11. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  12. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
38 more
  1. 2021Mobile-Former: Bridging MobileNet and Transformercited by 234
  2. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  3. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  4. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  5. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 185
  6. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
  7. 2021Combined Scaling for Zero-shot Transfer Learningcited by 182
  8. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  9. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 168
  10. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  11. 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 166
  12. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  13. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  14. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  15. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 146
  16. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  17. 2021Probabilistic two-stage detectioncited by 130
  18. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  19. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  20. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  21. 2022GRiT: A Generative Region-to-text Transformer for Object Understandingcited by 119
  22. 2021You Only Look One-level Featurecited by 116
  23. 2022EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformerscited by 116
  24. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 114
  25. 2022Global Tracking Transformerscited by 110
  26. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  27. 2023The Semantic Scholar Open Data Platformcited by 109
  28. 2021Distilling Object Detectors via Decoupled Featurescited by 105
  29. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 101
  30. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  31. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  32. 2021CAT: Cross Attention in Vision Transformercited by 92
  33. 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86
  34. 2021Cross-Modality Fusion Transformer for Multispectral Object Detectioncited by 86
  35. 2021Compressing Visual-linguistic Model via Knowledge Distillationcited by 85
  36. 2021ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spottingcited by 84
  37. 2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
  38. 2021Driving-Signal Aware Full-Body Avatarscited by 81

50 most cited of 1,018 All 1,018 (JSON)