Face Detection Dataset and Benchmark
The Face Detection Dataset and Benchmark (FDDB) dataset is a collection of labeled faces from Faces in the Wild dataset. It contains a total of 5171 face annotations, where images are also of various resolution, e.g. 363x450 and 229x410. The dataset incorporates a range of challenges, including difficult pose angles, out-of-focus faces and low resolution. Both greyscale and color images are included.
Source: A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications
Variants: FDDB
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Face Detection | Condensation-Net | Condensation-Net: Memory-Efficient Network Architecture with … | 2021-04-29 |
| Face Detection | IFQ-Tinier-YOLO(k=2) | IFQ-Net: Integrated Fixed-point Quantization Networks … | 2019-11-19 |
| Face Detection | LFFD | LFFD: A Light and Fast … | 2019-04-24 |
| Face Detection | DSFD | DSFD: Dual Shot Face Detector | 2018-10-24 |
| Face Detection | SRN | Selective Refinement Network for High … | 2018-09-07 |
| Face Detection | PyramidBox | PyramidBox: A Context-assisted Single Shot … | 2018-03-21 |
| Face Detection | Face R-FCN | Detecting Faces Using Region-based Fully … | 2017-09-14 |
| Face Detection | FaceBoxes | FaceBoxes: A CPU Real-time Face … | 2017-08-17 |
| Face Detection | S3FD | S$^3$FD: Single Shot Scale-invariant Face … | 2017-08-17 |
| Face Detection | HyperFace | HyperFace: A Deep Multi-task Learning … | 2016-03-03 |
| Face Detection | DPM | A Fast and Accurate Unconstrained … | 2014-08-06 |
Recent papers with results on this dataset: