HiNet: Hybrid Inherited Feature Learning Network for Facial Expression Recognition

Abstract

In this letter, we propose a novel lightweight network HiNet: hybrid inherited feature learning network and its variants: HiNet -ReLU, HiNet -Concat, Large Scale HiNet, 2 stack HiNet and 4 stack HiNet for facial expression recognition. In HiNet, we introduce the hybrid feature (HyFeat) block that follows a two - level hybrid structure to capture the local contextual information of expressive regions. In level -1, HyFeat block uses two different scaled conv filters to preserve the domain knowledge features for expressive regions. Similarly, level -2 captures the enriched features through refine edge variation of the receptive fields by employing another two filters. Thus, HyFeat block allows network to perpetuate prominent features of facial expressions and enhances the discriminability of the HiNet. Moreover, performance of the proposed HiNet is evaluated by conducting person dependent (PD) and person independent (PI) experiments on four datasets: CK+, MUG, AFEW and OULU respectively. Experimental results on CK+ dataset prove the adequacy of the proposed HiNet over its variants in terms of accuracy and computational complexity. Furthermore, the proposed HiNet uses approximately 5 /16, 1/138, 1/144 and 1/31 times less parameters as compared to the MobileNet, VGG -16, VGG - 19 and ResNet, respectively. The experimental and computational complexity analysis demonstrate the significant performance improvement of the proposed method over the state-of-the-art techniques in terms of recognition rate.