ASFD: Automatic and Scalable Face Detector
arXiv:2201.10781
Abstract
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.
arXiv commentACM MM2021
References in corpus (11)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Categorical Reparameterization with Gumbel-Softmax
- EfficientDet: Scalable and Efficient Object Detection
- RetinaFace: Single-stage Dense Face Localisation in the Wild
- Detecting Faces Using Region-based Fully Convolutional Networks
- Face Detection Using Improved Faster RCNN
- EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
- NAS-FCOS: Fast Neural Architecture Search for Object Detection
- RefineFace: Refinement Neural Network for High Performance Face Detection
Cited by in corpus (5)
- Sample and Computation Redistribution for Efficient Face Detection
- TinaFace: Strong but Simple Baseline for Face Detection
- Going Deeper Into Face Detection: A Survey
- Disentangle Your Dense Object Detector
- MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation