mlsanityData to 7 Oct 2026

PAFNet: An Efficient Anchor-Free Object Detector Guidance

arXiv 2104.13534 ↗First posted 28 Apr 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Object detection is a basic but challenging task in computer vision, which plays a key role in a variety of industrial applications. However, object detectors based on deep learning usually require greater storage requirements and longer inference time, which hinders its practicality seriously. Therefore, a trade-off between effectiveness and efficiency is necessary in practical scenarios. Considering that without constraint of pre-defined anchors, anchor-free detectors can achieve acceptable accuracy and inference speed simultaneously. In this paper, we start from an anchor-free detector called TTFNet, modify the structure of TTFNet and introduce multiple existing tricks to realize effective server and mobile solutions respectively. Since all experiments in this paper are conducted based on PaddlePaddle, we call the model as PAFNet(Paddle Anchor Free Network). For server side, PAFNet can achieve a better balance between effectiveness (42.2% mAP) and efficiency (67.15 FPS) on a single V100 GPU. For moblie side, PAFNet-lite can achieve a better accuracy of (23.9% mAP) and 26.00 ms on Kirin 990 ARM CPU, outperforming the existing state-of-the-art anchor-free detectors by significant margins. Source code is at https://github.com/PaddlePaddle/PaddleDetection.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 28 Apr 2021.

Builds on

30 of 42 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2015Fast R-CNNcited by 2,930
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2018YOLOv3: An Incremental Improvementcited by 2,652
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  11. 2019Searching for MobileNetV3cited by 1,984
  12. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
18 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  2. 2017Deformable Convolutional Networkscited by 1,481
  3. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  4. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  5. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  6. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  7. 2017Deep Layer Aggregationcited by 436
  8. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  9. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 380
  10. 2020GridMask Data Augmentationcited by 123
  11. 2020PP-YOLO: An Effective and Efficient Implementation of Object Detectorcited by 44
  12. 2018Contextual Hourglass Network for Semantic Segmentation of High Resolution Aerial Imagerycited by 42
  13. 2019FoveaBox: Beyond Anchor-based Object Detectorcited by 37
  14. 2017Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutescited by 22
  15. 2019Weighted boxes fusion: Ensembling boxes from different object detection modelscited by 20
  16. 2019Training-Time-Friendly Network for Real-Time Object Detectioncited by 17
  17. 2020The 1st Tiny Object Detection Challenge:Methods and Resultscited by 14
  18. 2020iffDetector: Inference-aware Feature Filtering for Object Detectioncited by 4

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 1; 2025: 1.

5 papers.

  1. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  2. 2025Ultralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognitioncited by 17
  3. 2022Extending One-Stage Detection with Open-World Proposalscited by 9
  4. 2023G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectorscited by 7
  5. 2024Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainercited by 6