mlsanityData to 7 Oct 2026

ASFD: Automatic and Scalable Face Detector

arXiv 2201.10781 ↗First posted 26 Jan 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Along with current multi-scale based detectors, Feature Aggregation and Enhancement (FAE) modules have shown superior performance gains for cutting-edge object detection. However, these hand-crafted FAE modules show inconsistent improvements on face detection, which is mainly due to the significant distribution difference between its training and applying corpus, COCO vs. WIDER Face. To tackle this problem, we essentially analyse the effect of data distribution, and consequently propose to search an effective FAE architecture, termed AutoFAE by a differentiable architecture search, which outperforms all existing FAE modules in face detection with a considerable margin. Upon the found AutoFAE and existing backbones, a supernet is further built and trained, which automatically obtains a family of detectors under the different complexity constraints. Extensive experiments conducted on popular benchmarks, WIDER Face and FDDB, demonstrate the state-of-the-art performance-efficiency trade-off for the proposed automatic and scalable face detector (ASFD) family. In particular, our strong ASFD-D6 outperforms the best competitor with AP 96.7/96.2/92.1 on WIDER Face test, and the lightweight ASFD-D0 costs about 3.1 ms, more than 320 FPS, on the V100 GPU with VGA-resolution images.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 37 of its 44 references that are in the map. First posted on arXiv 26 Jan 2022.

Builds on

37 of 44 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  10. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
25 more
  1. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  2. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  3. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  4. 2018Path Aggregation Network for Instance Segmentationcited by 796
  5. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  6. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  7. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  8. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  9. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 289
  10. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 258
  11. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  12. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  13. 2019RetinaFace: Single-stage Dense Face Localisation in the Wildcited by 164
  14. 2017S3FD: Single Shot Scale-invariant Face Detectorcited by 142
  15. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 140
  16. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 129
  17. 2018DSFD: Dual Shot Face Detectorcited by 115
  18. 2019DetNAS: Backbone Search for Object Detectioncited by 80
  19. 2018PyramidBox: A Context-assisted Single Shot Face Detectorcited by 57
  20. 2019NAS-FCOS: Fast Neural Architecture Search for Object Detectioncited by 53
  21. 2018Selective Refinement Network for High Performance Face Detectioncited by 21
  22. 2019RefineFace: Refinement Neural Network for High Performance Face Detectioncited by 21
  23. 2018Towards Highly Accurate and Stable Face Alignment for High-Resolution Videoscited by 19
  24. 2019EXTD: Extremely Tiny Face Detector via Iterative Filter Reusecited by 18
  25. 2020ACFD: Asymmetric Cartoon Face Detectorcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 3; 2025: 1.

9 papers.

  1. 2023PVG: Progressive Vision Graph for Vision Recognitioncited by 10
  2. 2022EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detectioncited by 5
  3. 2023Weakly-supervised Micro- and Macro-expression Spotting Based on Multi-level Consistencycited by 4
  4. 2023EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detectioncited by 3
  5. 2024Weak Supervision with Arbitrary Single Frame for Micro- and Macro-expression Spottingcited by 2
  6. 2024FDLite: A Single Stage Lightweight Face Detector Networkcited by 2
  7. 2024TopoNAS: Boosting Search Efficiency of Gradient-based NAS via Topological Simplificationcited by 1
  8. 2023EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detectioncited by 0
  9. 2025Archival Faces: Detection of Faces in Digitized Historical Documentscited by 0