Face Detection with End-to-End Integration of a ConvNet and a 3D Model

TL;DR

This paper introduces an end-to-end face detection method combining a ConvNet with a fixed 3D mean face model, improving proposal accuracy and structure-aware detection, achieving state-of-the-art results on benchmark datasets.

Contribution

It presents a novel integration of a 3D face model into a ConvNet for face detection, eliminating heuristic anchors and employing configuration pooling for better structural understanding.

Findings

Achieved state-of-the-art results on FDDB and AFW benchmarks.

Eliminated heuristic anchor box design using 3D face model.

Improved detection accuracy with configuration pooling.

Abstract

This paper presents a method for face detection in the wild, which integrates a ConvNet and a 3D mean face model in an end-to-end multi-task discriminative learning framework. The 3D mean face model is predefined and fixed (e.g., we used the one provided in the AFLW dataset). The ConvNet consists of two components: (i) The face pro- posal component computes face bounding box proposals via estimating facial key-points and the 3D transformation (rotation and translation) parameters for each predicted key-point w.r.t. the 3D mean face model. (ii) The face verification component computes detection results by prun- ing and refining proposals based on facial key-points based configuration pooling. The proposed method addresses two issues in adapting state- of-the-art generic object detection ConvNets (e.g., faster R-CNN) for face detection: (i) One is to eliminate the heuristic design of prede- fined anchor boxes in the region proposals network (RPN) by exploit- ing a 3D mean face model. (ii) The other is to replace the generic RoI (Region-of-Interest) pooling layer with a configuration pooling layer to respect underlying object structures. The multi-task loss consists of three terms: the classification Softmax loss and the location smooth l1 -losses [14] of both the facial key-points and the face bounding boxes. In ex- periments, our ConvNet is trained on the AFLW dataset only and tested on the FDDB benchmark with fine-tuning and on the AFW benchmark without fine-tuning. The proposed method obtains very competitive state-of-the-art performance in the two benchmarks.