retinaface-r50
by deepinsight
Single-stage face detection with landmark localization
deepinsight/retinaface-r50mixpeek://face_identity@v1/deepinsight_retinaface_r50Overview
RetinaFace is a robust single-stage face detector that simultaneously performs face detection, 2D facial landmark localization, and 3D face reconstruction. It achieves state-of-the-art performance on WIDER FACE benchmark.
On Mixpeek, RetinaFace powers face detection and identity matching across video and image content, enabling face-based search and filtering in retrieval pipelines.
Architecture
ResNet-50 backbone with multi-task learning heads: face classification, bounding box regression, 5-point landmark localization, and optional 3D face mesh regression. Uses Feature Pyramid Network (FPN) for multi-scale detection.
Mixpeek SDK Integration
import { Mixpeek } from "mixpeek";const mx = new Mixpeek({ apiKey: "API_KEY" });await mx.collections.ingest({collection_id: "my-collection",source: { url: "https://example.com/video.mp4" },feature_extractors: [{name: "face_detection",version: "v1",params: {model_id: "deepinsight/retinaface-r50"}}]});
Capabilities
- High-accuracy face detection across scales
- 5-point facial landmark localization
- Face embedding extraction for identity matching
- Handles partial occlusion and extreme poses
Use Cases on Mixpeek
Benchmarks
| Dataset | Metric | Score | Source |
|---|---|---|---|
| WIDER Face (Hard) | AP | 91.4% | Deng et al., 2020 — Table 5 |
| WIDER Face (Easy) | AP | 96.5% | Deng et al., 2020 — Table 5 |
Performance
Specification
Research Paper
RetinaFace: Single-shot Multi-level Face Localisation in the Wild
arxiv.orgBuild a pipeline with retinaface-r50
Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.
Open Pipeline Builder