A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain Knowledge

Recent advancements in deep learning have significantly increased the capabilities of face recognition. However, face recognition in an unconstrained environment is still an active research challenge. Covariates such as pose and low resolution have received significant attention, but “disguise” is considered an onerous covariate of face recognition. One primary reason for this is the unavailability of large and representative databases. To address the problem of recognizing disguised faces, we propose an active learning framework A-LINK, that intelligently selects training samples from the target domain data, such that the decision boundary does not overfit to a particular set of variations, and better generalizes to encode variability. The framework further applies domain adaptation with the actively selected training samples to fine-tune the network. We demonstrate the effectiveness of the proposed framework on DFW and Multi-PIE datasets with state-of-the-art models such as LCSSE and DenseNet.



Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Heterogeneous Face Recognition CMU-MPIE A-LINK 16x16 Accuracy 92.4 # 1
24x24 Accuracy 92.6 # 1
32x32 Accuracy 92.8 # 1
48x48 Accuracy 92.9 # 1
Heterogeneous Face Recognition Disguised Faces in the Wild A-LINK GAR @0.1% FAR Impersonation 75.38 # 1
GAR @0.1% FAR Obfuscation 72.13 # 2
GAR @0.1% FAR Overall 72.72 # 2
GAR @1% FAR Impersonation 95.73 # 2
GAR @1% FAR Obfuscation 88.97 # 2
GAR @1% FAR Overall 89.3 # 2