Occlusion Coherence: Detecting and Localizing Occluded Faces

TL;DR

This paper introduces a hierarchical deformable part model that explicitly incorporates occlusion modeling, significantly improving face detection and landmark localization accuracy in occluded scenarios.

Contribution

It presents a novel explicit occlusion model within a deformable part framework, enabling effective training with synthetic occlusions and improved detection of occluded faces.

Findings

Outperforms existing methods on occluded face detection benchmarks.

Maintains competitive accuracy on unoccluded face detection.

Effectively models occlusion patterns for better recognition.

Abstract

The presence of occluders significantly impacts object recognition accuracy. However, occlusion is typically treated as an unstructured source of noise and explicit models for occluders have lagged behind those for object appearance and shape. In this paper we describe a hierarchical deformable part model for face detection and landmark localization that explicitly models part occlusion. The proposed model structure makes it possible to augment positive training data with large numbers of synthetically occluded instances. This allows us to easily incorporate the statistics of occlusion patterns in a discriminatively trained model. We test the model on several benchmarks for landmark localization and detection including challenging new data sets featuring significant occlusion. We find that the addition of an explicit occlusion model yields a detection system that outperforms existing approaches for occluded instances while maintaining competitive accuracy in detection and landmark localization for unoccluded instances.