Download
This repository implements the Tiny Face Detector (from Hu & Ramanan, CVPR 2017) in MATLAB (using MatConvNet). The method is designed to detect tiny faces (i.e. very small-scale faces) by combining multi-scale context modeling, foveal descriptors, and scale enumeration strategies. It provides training/testing scripts, a demo (tiny_face_detector.m), model loading, evaluation on WIDER FACE, and supporting utilities (e.g. cnn_widerface_eval.m). The code depends on MatConvNet, which must be compiled (with GPU / CUDA / cuDNN support) for full performance. Pretrained model provided (ResNet101-based, plus alternatives). Demo and evaluation scripts for benchmark datasets. Use of “foveal descriptors” to incorporate context for low-resolution faces. Pretrained model provided (ResNet101-based, plus alternatives).
Features
- Detection of very small faces (tiny scale)
- Multi-scale enumeration strategy (e.g. scaling input, interpolations)
- Use of “foveal descriptors” to incorporate context for low-resolution faces
- Pretrained model provided (ResNet101-based, plus alternatives)
- Demo and evaluation scripts for benchmark datasets
- Integration with MatConvNet, with GPU / MEX support
Project Samples
