Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Network

TL;DR

This paper introduces a mask learning approach using a Pairwise Differential Siamese Network to improve face recognition accuracy under occlusions by identifying and discarding corrupted features.

Contribution

It proposes a novel mask learning strategy with a dictionary of occlusion-related feature masks, enhancing robustness of face recognition models against occlusions.

Findings

Significantly outperforms existing methods on occluded face datasets.

Effectively identifies and removes occlusion-corrupted features.

Demonstrates robustness on both synthetic and real-world occlusion scenarios.

Abstract

Deep Convolutional Neural Networks (CNNs) have been pushing the frontier of the face recognition research in the past years. However, existing general CNN face models generalize poorly to the scenario of occlusions on variable facial areas. Inspired by the fact that a human visual system explicitly ignores occlusions and only focuses on non-occluded facial areas, we propose a mask learning strategy to find and discard the corrupted feature elements for face recognition. A mask dictionary is firstly established by exploiting the differences between the top convoluted features of occluded and occlusion-free face pairs using an innovatively designed Pairwise Differential Siamese Network (PDSN). Each item of this dictionary captures the correspondence between occluded facial areas and corrupted feature elements, which is named Feature Discarding Mask (FDM). When dealing with a face image with random partial occlusions, we generate its FDM by combining relevant dictionary items and then multiply it with the original features to eliminate those corrupted feature elements. Comprehensive experiments on both synthesized and realistic occluded face datasets show that the proposed approach significantly outperforms the state-of-the-arts.