Research map / Architectures and efficiency / CNN design
SSH: Single Stage Headless Face Detector
Mahyar Najibi, Pouya Samangouei, Rama Chellappa, Larry S. Davis
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add image pyramid at inference to SSH | SSH (VGG-16) · WIDER val (hard) | AP: 81.4 -> 84.5 | Improved |
| add multiple detection modules M1 and M3 on different strides (vs only M2 from conv5-3) (ablation) | SSH (VGG-16) · WIDER val (hard) | AP: AP drops by ~12.8% | Improved |
| add the context module (5x5 and 7x7 receptive field via sequential 3x3 convs) (ablation) | SSH (VGG-16) · WIDER val | mAP: more than half a percent | Improved |
| add OHEM for anchor selection in each detection module (ablation) | SSH (VGG-16) · WIDER val | AP | Improved |
| add conv4-3/conv5-3 feature fusion for module M1 (ablation) | SSH (VGG-16) · WIDER val | AP | Improved |
| use finer anchor scale sets (5 scales per module) instead of 2 (ablation) | SSH (VGG-16) · WIDER val | AP | Hurt |
| use SSH without pyramid instead of HR (VGG-16) with pyramid | SSH (VGG-16) · WIDER val (hard) | AP: outperforms HR VGG-16 by 5.7%, 6.3%, and 6.5% | Improved |
| use multiple aspect ratios for anchors (not used) | SSH (VGG-16) · WIDER | AP | No clear effect |
Closest papers by meaning
- DamoFD: Digging into Backbone Design on Face Detection (ICLR 2023 · similarity 0.85)
- S3FD: Single Shot Scale-Invariant Face Detector (ICCV 2017 · similarity 0.84)
- KPNet: Towards Minimal Face Detector (AAAI 2020 · similarity 0.84)
- SSD: Single Shot MultiBox Detector (ECCV 2016 · similarity 0.83)
- BFBox: Searching Face-Appropriate Backbone and Feature Pyramid Network for Face Detector (CVPR 2020 · similarity 0.83)
- CryptoFace: End-to-End Encrypted Face Recognition (CVPR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
